arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.06019cs.CVcs.RO
收藏

LS-VO:学习稠密光学子空间用于鲁棒视觉里程计估计

LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation

University of Perugia(佩鲁贾大学)

Gabriele Costante, Thomas A. Ciarfuglia

摘要:

这项工作提出了一种新的深度网络架构来解决相机自我运动估计问题。运动估计网络通常从图像序列开始学习类似于光流(OF)场的特征。这个OF可以用一个低维的潜在空间来描述。以前的研究已经展示了如何找到这个空间的线性近似。我们建议使用自动编码器网络来找到OF流形的非线性表示。此外,我们建议学习潜在空间与估计任务,使学习的OF功能成为一个更强大的描述OF输入。我们称这种新颖的架构为LS-VO。实验表明,LS-VO实现了相当大的提高性能相对于基线,而估计网络的参数的数量只略有增加。

英文摘要:

This work proposes a novel deep network architecture to solve the camera Ego-Motion estimation problem. A motion estimation network generally learns features similar to Optical Flow (OF) fields starting from sequences of images. This OF can be described by a lower dimensional latent space. Previous research has shown how to find linear approximations of this space. We propose to use an Auto-Encoder network to find a non-linear representation of the OF manifold. In addition, we propose to learn the latent space jointly with the estimation task, so that the learned OF features become a more robust description of the OF input. We call this novel architecture LS-VO. The experiments show that LS-VO achieves a considerable increase in performances in respect to baselines, while the number of parameters of the estimation network only slightly increases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑