Proceedings of the Korean Institute of Information and Commucation Sciences Conference (한국정보통신학회:학술대회논문집)
- Volume 9 Issue 1
- /
- Pages.816-819
- /
- 2005
Coordinates Transformation and Correction Techniques of the Distorted Omni-directional Image
왜곡된 전 방향 영상에서의 좌표 변환 및 보정
- Cha, Sun-Hee (Dept of Computer Engineering, Pusan National University) ;
- Park, Young-Min (Dept of Computer Engineering, Pusan National University) ;
- Cha, Eui-Young (Dept of Computer Engineering, Pusan National University)
- Published : 2005.05.27
Abstract
This paper proposes a coordinate correction technique using the transformation of 3D parabolic coordinate function and BP(Back Propagation) neural network in order to solve space distortion problem caused by using catadioptric camera. Although Catadioptric camera can obtain omni-directional image at all directions of 360 degrees, it makes an image distorted because of an external form of lens itself. Accordingly, To obtain transformed ideal distance coordinate information from distorted image on 3 dimensional space, we use coordinate transformation function that uses coordinates of a focus at mirror in the shape of parabolic plane and another one which projected into the shape of parabolic from input image. An error of this course is modified by BP neural network algorithm.
본 논문에서는 카타디옵트릭 카메라를 사용할 때 발생하는 공간 왜곡 문제를 해결하기 위해 3차원 포물면 좌표 변환 함수와 신경회로망을 이용한 좌표 변환 및 보정 기법을 제안한다. 본 연구에서 사용하는 포물면 거울을 이용한 카타디옵트릭 카메라는 360