一种结合等变滤波和视觉观测网络的混合视觉惯性里程计  

A hybrid visual-inertial odometry combining equivariant filter and visual observation network

在线阅读下载全文

作  者:胡建朗 罗亚荣 郭迟[1,2,3] 刘经南 HU Jianlang;LUO Yarong;GUO Chi;LIU Jingnan(School of Computer Science,Wuhan University,Wuhan 430079,China;GNSS Research Center,Wuhan University,Wuhan 430079,China;Hubei Luojia Laboratory,Wuhan 430079,China)

机构地区:[1]武汉大学计算机学院,武汉430079 [2]武汉大学卫星导航定位技术研究中心,武汉430079 [3]湖北珞珈实验室,武汉430079

出  处:《导航定位与授时》2024年第6期28-46,共19页Navigation Positioning and Timing

基  金:中国博士后科学基金项目(2023TQ0248);电磁能技术全国重点实验室稳定支持科研项目(614221723040101);湖北珞珈实验室开放基金(230100007)。

摘  要:传统的面向惯导的滤波器在设计时通常没有考虑零偏状态的几何性质,针对这一问题,提出了新的群以及群作用,并以此为基础推导了一种新的等变滤波方法。为了验证该滤波算法的性能,构建了一个基于学习的结合等变滤波和视觉观测网络的视觉惯性里程计系统,名为Deep-EqF-VIO。首先,构建了流形上的导航状态动力学系统,其次根据等变滤波原理推导了等变滤波方法,最后结合视觉观测网络构建了视觉惯性里程计系统。为了进一步提高系统性能,提出了一种融合稠密光流伪标签的预训练方法,通过光流估计任务引导视觉观测网络从输入图像中提取更加通用的几何运动特征。实验结果表明,在大多数场景中,Deep-EqF-VIO相较于同类方法有更好的表现,并且在使用预训练方法进行重新训练后,性能得到了进一步的改善,误差下降率最大达到了49.80%,具有一定的应用前景。Traditional geometric filter algorithms are usually designed without considering the geometric properties of bias states.To deal with this problem,a group and a group action are proposed,and a new equivariant filter method is derived.To evaluate the performance of this filter algorithm,a visual-inertial odometry system based on an equivariant filter and a visual observation network,named Deep-EqF-VIO,is developed.Firstly,a navigation state dynamics system is constructed on the manifold,then an equivariant filter method is derived by the equivariant filter principle,and finally a visual-inertial odometry system is constructed by combining with a visual observation network.In order to further improve the performance of the system,a pretraining method incorporating with dense optical flow pseudo-labels is proposed.This method guides the visual observation network to extract more generalized geometric motion features from input images via the optical flow estimation task.Experimental results show that Deep-EqF-VIO achieves the best accuracy in most scenes compared to similar algorithms.After retraining the VIO system by using the proposed pre-training method,the VIO performance can be further improved,with the maximum error reduction rate reaching 49.80%.This method has a certain degree of application potential.

关 键 词:视觉惯性里程计 等变滤波 光流估计 预训练 深度学习 

分 类 号:P223[天文地球—大地测量学与测量工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象