Proceedings of the Korea Information Processing Society Conference (한국정보처리학회:학술대회논문집)
- 2015.10a
- /
- Pages.1350-1353
- /
- 2015
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
A Study of Detecting The Fish Robot Position Using The Object Boundary Algorithm
물체 형상인식 알고리즘을 이용한 물고기 로봇 위치 검출에 관한 연구
- Amarnath, Varma Angani (Depart of ICT Creative Design, Graduate School, Busan University of Foreign Studies) ;
- Kang, Min Jeong (Depart of Digital Media Engineering, Busan University of Foreign Studies) ;
- Shin, Kyoo Jae (Depart of ICT Creative Design, Graduate School, Busan University of Foreign Studies)
- 아마르나 바르마 앙가니 (부산외국어대학교 일반대학원, ICT 창의융합학과) ;
- 강민정 (부산외국어대학교 디지털미디어공학부) ;
- 신규재 (부산외국어대학교 일반대학원, ICT 창의융합학과)
- Published : 2015.10.28
Abstract
In this paper, we have researched about how to detect the fish robot objects in aquarium. We had used designed fish robots DOMI ver1.0, which had researched and developed for aquarium underwater robot. The model of the robot fish is analysis to maximize the momentum of the robot fish and the body of the robot is designed through the analysis of the biological fish swimming. We are planned to non-external equipment to find the position and manipulated the position using creating boundary to fish robot to detect the fish robot objects. Also, we focused the detecting fish robot in aquarium by using boundary algorithm. In order to the find the object boundary, it is filtering the video frame to picture frames and changing the RGB to gray. Then, applied the boundary algorithm stand of equations which operates the boundary for objects. We called these procedures is kind of image processing that can distinguish the objects and background in the captured video frames. It was confirmed that excellent performance in the field test such as filtering image, object detecting and boundary algorithm.
Keywords