An improved FAST feature extraction based on RANSAC method of vision/SINS integrated navigation system in GNSS-denied environments
An improved FAST feature extraction based on RANSAC method of vision/SINS integrated navigation system in GNSS-denied environments
复制标题
GNSS环境下视觉/SINS组合导航系统基于RANSAC方法的改进FAST特征提取
DOI：
10.1016/j.asr.2017.05.017
复制
发表时间：
2017-12-15
影响因子：
2.6
通讯作者：
Gao, Wei
中科院分区：
文献类型：
--
作者：
Sun, Qian;Zhang, Ya;Gao, Wei
捷联惯性导航系统（SINS）和全球导航卫星系统（GNSS）组合导航系统以其众多优点在现代运动定位和导航中得到了广泛的应用，但GNSS信号容易受到周围环境的干扰或阻塞，这将大大降低系统的精度。因此，有必要对其他辅助技术进行研究。随着数字成像传感器和计算机技术的飞速发展，视觉/捷联惯导集成系统的重要性日益凸显。特征提取是组合导航的关键和基础技术，好的特征提取器可以提高组合导航的精度。为了提高特征提取的鲁棒性和准确性，本文提出了一种改进的基于随机样本一致性（RANSAC）方法的加速段测试特征提取（FAST）来去除不匹配点。并通过实验对该方法的性能进行了评价。实验结果表明，所提出的特征提取器不仅能有效地提取特征，而且能有效地减小定位误差，使得基于RANSAC的FAST特征提取方法可行且高效。(c) 2017年价格。Elsevier Ltd.出版。版权所有。
Although Strapdown Inertial Navigation System (SINS) and Global Navigation Satellite System (GNSS) integrated navigation system has been widely used in modern kinematic positioning and navigation due to its numerous advantages, the GNSS signal is easily disturbed or blocked by the surroundings, which will reduce the system accuracy significantly. So some other alternated aiding techniques should be studied on. With the rapid development of the digital imaging sensors and computer techniques, the vision/SINS integrated system is gradually important. Since the feature extraction is the key and basic technique, superior feature extractor can improve the integrated navigation accuracy. In order to improve the robustness and accuracy of the feature extraction, an improved Features from Accelerated Segment Test (FAST) feature extraction based on the Random Sample Consensus (RANSAC) method is proposed to remove the mismatched points in this manuscript. Furthermore, the performance of this new method has been estimated through experiments. And the results have shown that the proposed feature extractor cannot only effectively extract features, but also reduce the positioning error availably, making the proposed FAST feature extraction based on RANSAC feasible and efficient. (C) 2017 COSPAR. Published by Elsevier Ltd. All rights reserved.