CodedVO: Coded Visual Odometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shah, Sachin, Rajyaguru, Naitri, Singh, Chahat Deep, Metzler, Christopher, Aloimonos, Yiannis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916336338206720
author Shah, Sachin
Rajyaguru, Naitri
Singh, Chahat Deep
Metzler, Christopher
Aloimonos, Yiannis
author_facet Shah, Sachin
Rajyaguru, Naitri
Singh, Chahat Deep
Metzler, Christopher
Aloimonos, Yiannis
contents Autonomous robots often rely on monocular cameras for odometry estimation and navigation. However, the scale ambiguity problem presents a critical barrier to effective monocular visual odometry. In this paper, we present CodedVO, a novel monocular visual odometry method that overcomes the scale ambiguity problem by employing custom optics to physically encode metric depth information into imagery. By incorporating this information into our odometry pipeline, we achieve state-of-the-art performance in monocular visual odometry with a known scale. We evaluate our method in diverse indoor environments and demonstrate its robustness and adaptability. We achieve a 0.08m average trajectory error in odometry evaluation on the ICL-NUIM indoor odometry dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CodedVO: Coded Visual Odometry
Shah, Sachin
Rajyaguru, Naitri
Singh, Chahat Deep
Metzler, Christopher
Aloimonos, Yiannis
Robotics
Computer Vision and Pattern Recognition
Autonomous robots often rely on monocular cameras for odometry estimation and navigation. However, the scale ambiguity problem presents a critical barrier to effective monocular visual odometry. In this paper, we present CodedVO, a novel monocular visual odometry method that overcomes the scale ambiguity problem by employing custom optics to physically encode metric depth information into imagery. By incorporating this information into our odometry pipeline, we achieve state-of-the-art performance in monocular visual odometry with a known scale. We evaluate our method in diverse indoor environments and demonstrate its robustness and adaptability. We achieve a 0.08m average trajectory error in odometry evaluation on the ICL-NUIM indoor odometry dataset.
title CodedVO: Coded Visual Odometry
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.18240