Notes on iterative closest algorithm

Abstract

Point clouds are commontly used in many areas of technical practice. Nowadays, the common applications are in area of autonomous cars and 3D terrain or object modelling. During the scanning process, the scanning device or object is moving. So, the problem of precise point cloud registration arises. In this article, we describe Iterative Closest Point (ICP) algorithm that is suitable for fine registration. We introduce some of the improvements that leads to higher precision, speed computation and efficiency.Point clouds are commontly used in many areas of technical practice. Nowadays, the common applications are in area of autonomous cars and 3D terrain or object modelling. During the scanning process, the scanning device or object is moving. So, the problem of precise point cloud registration arises. In this article, we describe Iterative Closest Point (ICP) algorithm that is suitable for fine registration. We introduce some of the improvements that leads to higher precision, speed computation and efficiency.