ICP IMAGE PROCESSING METHOD BASED ON ITERATIVE CLOSEST POINT ICP TECHNIQUE

In various embodiments of an image processing method and apparatus, first and second point clouds representing respective images of a scene/object from different viewpoints are obtained. Extracted features points from the first point cloud are matched with extracted feature points from the second po...

Full description

Saved in:
Bibliographic Details
Main Authors LEVY NATHAN HENRI, AFLALO YONATHAN
Format Patent
LanguageEnglish
Korean
Published 26.06.2019
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:In various embodiments of an image processing method and apparatus, first and second point clouds representing respective images of a scene/object from different viewpoints are obtained. Extracted features points from the first point cloud are matched with extracted feature points from the second point cloud by using depth-based weighting as a part of an iterative closest point (ICP) initiation process. The first and second point clouds are then further ICP-processed by using results of the initiation process to generate at least one coordinate-transformed point cloud. 이미지 프로세싱 방법 및 장치의 다양한 실시 예들에 있어서, 상이한 시점들로부터 장면/객체의 각각의 이미지들을 나타내는 제 1 및 제 2 포인트 클라우드들이 얻어진다. ICP 초기 프로세스의 일부로서 깊이 기반의 가중치 할당을 이용하여, 제 1 포인트 클라우드로부터 추출된 특징점들은 제 2 포인트 클라우드로부터 추출된 특징점들과 정합된다. 그 다음 제 1 및 제 2 포인트 클라우드들은 초기 프로세스의 결과들을 이용하여 더 ICP 처리되어 적어도 하나의 좌표 변환된 포인트 클라우드를 생성한다.
Bibliography:Application Number: KR20180078786