Saved in:
Bibliographic Details
Main Authors: Bruno, Hudson M. S., Colombini, Esther L., Givigi Jr, Sidney N.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.12520
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917804982140928
author Bruno, Hudson M. S.
Colombini, Esther L.
Givigi Jr, Sidney N.
author_facet Bruno, Hudson M. S.
Colombini, Esther L.
Givigi Jr, Sidney N.
contents Visual Simultaneous Localization and Mapping (VSLAM) is a fundamental technology for robotics applications. While VSLAM research has achieved significant advancements, its robustness under challenging situations, such as poor lighting, dynamic environments, motion blur, and sensor failures, remains a challenging issue. To address these challenges, we introduce a novel RGB-D dataset designed for evaluating the robustness of VSLAM systems. The dataset comprises real-world indoor scenes with dynamic objects, motion blur, and varying illumination, as well as emulated camera failures, including lens dirt, condensation, underexposure, and overexposure. Additionally, we offer open-source scripts for injecting camera failures into any images, enabling further customization by the research community. Our experiments demonstrate that ORB-SLAM2, a traditional VSLAM algorithm, and TartanVO, a Deep Learning-based VO algorithm, can experience performance degradation under these challenging conditions. Therefore, this dataset and the camera failure open-source tools provide a valuable resource for developing more robust VSLAM systems capable of handling real-world challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12520
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QueensCAMP: an RGB-D dataset for robust Visual SLAM
Bruno, Hudson M. S.
Colombini, Esther L.
Givigi Jr, Sidney N.
Computer Vision and Pattern Recognition
Artificial Intelligence
Visual Simultaneous Localization and Mapping (VSLAM) is a fundamental technology for robotics applications. While VSLAM research has achieved significant advancements, its robustness under challenging situations, such as poor lighting, dynamic environments, motion blur, and sensor failures, remains a challenging issue. To address these challenges, we introduce a novel RGB-D dataset designed for evaluating the robustness of VSLAM systems. The dataset comprises real-world indoor scenes with dynamic objects, motion blur, and varying illumination, as well as emulated camera failures, including lens dirt, condensation, underexposure, and overexposure. Additionally, we offer open-source scripts for injecting camera failures into any images, enabling further customization by the research community. Our experiments demonstrate that ORB-SLAM2, a traditional VSLAM algorithm, and TartanVO, a Deep Learning-based VO algorithm, can experience performance degradation under these challenging conditions. Therefore, this dataset and the camera failure open-source tools provide a valuable resource for developing more robust VSLAM systems capable of handling real-world challenges.
title QueensCAMP: an RGB-D dataset for robust Visual SLAM
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.12520