文档介绍：
EMD-SIFT based Deep Space Image Matching Method#
Yin Mengzheng1, Wu Xuechen1, Li Xiaoyu1, Feng Hongqi2, Wang Qiang1**
(1. Department of Control Science and Engineering, Harbin Institute of Technology,
5
10
Harbin 150001;
2. China Astronaut Research and Training Center, Beijing 100000)
Abstract: The paper puts forward a kind of scale invariant feature matching method for asteroid image
sequences. In which we apply EMD (Empirical Mode position) to extract the features from
image sequences, SIFT (scale invariant feature transform) to match the extracted features, and affine
transform to stretch and rotate the images. We can achieve a global view of the scanned asteroid
surface. Experiment results demonstrate the excellent performance of the EMD-SIFT based method in
mosaicking the asteroid image sequences.
Keywords: Empirical Mode position; Scale Invariant Feature Transform; Image Match;Deep
Space Exploration
15
0 Introduction
Deep space exploration is the first step in human understanding of the Earth, the solar system
and the universe. Through deep space exploration, human can study the solar system and the
origin, evolution and current situation of the universe[1]. No matter from the long term or the
20
25
30
35
40
reality, the research activities have a significant meaning. In deep space exploration research, there
is a variety of information, in