Landmark selection and matching for aiding lunar surface navigation

2015 IEEE International Conference on Information and Automation Pub Date : 2015-10-01 DOI:10.1109/ICINFA.2015.7279499

Yujian Feng, Jianhua Zhang, Qinhu Ren, Zhen Xie, Sheng Liu, Shengyong Chen

引用次数: 1

Abstract

The visual navigation on the lunar surface is a natural way to alleviate the accumulated error raised by the inertial navigation device. However, it is difficult to find distinctive landmarks for effective visual navigation due to the similar and textureless terrains on the lunar surface. In this paper, a novel algorithm is proposed to solve such a problem. Firstly, the local invariant features extract. Next, an improved density cluster technology employed is to initial landmark patches. Finally, we choose the most distinctive and robust patch by optimizing an objective function. For meeting the real time requirement, we also design an effective strategy to reduce the number of local invariant features. The proposed method evaluates in the lunar surface map with 50 meters accuracy. The experimental results exhibit satisfactory performance in terms of matching accuracy.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

辅助月球表面导航的地标选择与匹配

月球表面视觉导航是缓解惯性导航装置积累误差的一种自然途径。然而，由于月球表面的地形相似且无纹理，很难找到有效的视觉导航的独特地标。本文提出了一种新的算法来解决这一问题。首先，提取局部不变特征。其次，采用改进的密度聚类技术初始化地标斑块。最后，通过优化目标函数选择最具特征和鲁棒性的patch。为了满足实时性的要求，我们还设计了一种有效的策略来减少局部不变特征的数量。所提出的方法在月球表面地图上进行了精度为50米的评估。实验结果表明，该方法在匹配精度方面取得了令人满意的效果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2015 IEEE International Conference on Information and Automation

自引率

0.00%

发文量

期刊最新文献

Control DC bus voltage of active power filter with a novel PID control A generalized pruning algorithm for extreme learning machine BP and RBF neural network in decoupling research on flexible tactile sensors A new hybrid tracking strategy based on Pulse Coupled Neural Network The designing of the state machine for multi-frequency IIR low-pass digital filter