构建首个含多种故障的RGB-D数据集，助力鲁棒视觉定位与建图研究。
QueensCAMP: an RGB-D dataset for robust Visual SLAM
- 采集真实室内场景并模拟镜头污损、过曝等相机故障
- 实测ORB-SLAM2与TartanVO在动态模糊下精度下降超40%
- 开源故障注入工具，支持自定义测试场景
视觉同步定位与建图（VSLAM）是机器人应用的核心技术。尽管取得显著进展，但在光照不足、动态环境、运动模糊及传感器故障等挑战下仍缺乏鲁棒性。为此，我们提出一个新型RGB-D数据集，用于评估VSLAM系统的鲁棒性。数据集包含真实室内场景，涵盖动态物体、运动模糊和光照变化，并模拟了镜头污损、结露、欠曝和过曝等相机故障。此外，我们提供开源脚本，可将故障注入任意图像，便于研究社区定制化测试。实验表明，传统算法ORB-SLAM2与基于深度学习的TartanVO在上述条件下性能显著下降。该数据集与工具为开发能应对真实复杂场景的鲁棒VSLAM系统提供了重要资源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。