ADUGS-VINS: Generalized Visual-Inertial Odometry for Robust Navigation in Highly Dynamic and Complex Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Rui, Liu, Jingbin, Xie, Junbin, Zhang, Jianyu, Hu, Yingze, Zhao, Jiele
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910853213716480
author Zhou, Rui
Liu, Jingbin
Xie, Junbin
Zhang, Jianyu
Hu, Yingze
Zhao, Jiele
author_facet Zhou, Rui
Liu, Jingbin
Xie, Junbin
Zhang, Jianyu
Hu, Yingze
Zhao, Jiele
contents Visual-inertial odometry (VIO) is widely used in various fields, such as robots, drones, and autonomous vehicles. However, real-world scenes often feature dynamic objects, compromising the accuracy of VIO. The diversity and partial occlusion of these objects present a tough challenge for existing dynamic VIO methods. To tackle this challenge, we introduce ADUGS-VINS, which integrates an enhanced SORT algorithm along with a promptable foundation model into VIO, thereby improving pose estimation accuracy in environments with diverse dynamic objects and frequent occlusions. We evaluated our proposed method using multiple public datasets representing various scenes, as well as in a real-world scenario involving diverse dynamic objects. The experimental results demonstrate that our proposed method performs impressively in multiple scenarios, outperforming other state-of-the-art methods. This highlights its remarkable generalization and adaptability in diverse dynamic environments, showcasing its potential to handle various dynamic objects in practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19289
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ADUGS-VINS: Generalized Visual-Inertial Odometry for Robust Navigation in Highly Dynamic and Complex Environments
Zhou, Rui
Liu, Jingbin
Xie, Junbin
Zhang, Jianyu
Hu, Yingze
Zhao, Jiele
Computer Vision and Pattern Recognition
Visual-inertial odometry (VIO) is widely used in various fields, such as robots, drones, and autonomous vehicles. However, real-world scenes often feature dynamic objects, compromising the accuracy of VIO. The diversity and partial occlusion of these objects present a tough challenge for existing dynamic VIO methods. To tackle this challenge, we introduce ADUGS-VINS, which integrates an enhanced SORT algorithm along with a promptable foundation model into VIO, thereby improving pose estimation accuracy in environments with diverse dynamic objects and frequent occlusions. We evaluated our proposed method using multiple public datasets representing various scenes, as well as in a real-world scenario involving diverse dynamic objects. The experimental results demonstrate that our proposed method performs impressively in multiple scenarios, outperforming other state-of-the-art methods. This highlights its remarkable generalization and adaptability in diverse dynamic environments, showcasing its potential to handle various dynamic objects in practical applications.
title ADUGS-VINS: Generalized Visual-Inertial Odometry for Robust Navigation in Highly Dynamic and Complex Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.19289