국내 최대 기계 및 로봇 연구정보

기술보고서

기술보고서 게시판 내용
타이틀	A Method for Eliminating Noise from Multiple Images for Reconstructing 3-D Objects
저자	Susumu Yoshikawa, Toshio Isobe, Kohzo Homma
Keyword	Computer Vision; Image Processing; Eliminating Noise; Reconstruction of 3-D objects; Stereo-Vision
URL	http://send.nal.go.jp/send/jpn/dlpdf.php3/naltr0001354.pdf?id=NALTR0001354
보고서번호	NAL TR-1354
발행년도	1998.8
출처	NAL (National Aerospace Laboratory of Japan)
ABSTRACT	Reconstructing 3-D objects from image data is one of the most important problems in enabling a robot to recognize the environment and work independently in a rocket. As the basis for reconstructing 3-D objects, a new method for identifying edges in images is presented. This method consists of the following three subprocedures: (1) Differences of b using multi image data obtained by a camera moving on a rail. An experimental camera system has been constructed in order to confirm the theoretical consideration, and various examples have been tested. The results show that almost all noise can be recognized and eliminated.