BriefGPT.xyz
Mar, 2019
无监督单目视觉里程计的位姿图优化
Pose Graph Optimization for Unsupervised Monocular Visual Odometry
HTML
PDF
Yang Li, Yoshitaka Ushiku, Tatsuya Harada
TL;DR
本文提出一种基于无监督学习的单目视觉里程计系统,结合图优化和回路检测,利用神经网络构建一个包含多视图6DoF约束的窗口位姿图,并提出了一种姿态周期一致性损失来改善性能和鲁棒性,进而构建全局位姿图进行优化,实验结果表明该方法具有良好的性能和精度。
Abstract
unsupervised learning
based monocular
visual odometry
(VO) has lately drawn significant attention for its potential in label-free leaning ability and robustness to camera parameters and environmental variations.
→