通过3D语义几何投票，有效剔除动态物体提升复杂环境定位精度
V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D Semantic Geometry Voting
- 用空间推理的霍夫投票识别可能移动/静态物体
- 基于切比雪夫距离检测物体内部运动噪声并优化静态点云
- 在动态序列上优于最新SLAM方法，适合机器人导航场景
在高度动态环境中进行同时定位与建图（SLAM）面临移动物体与相机位姿间复杂关联的挑战。现有方法虽尝试应对，但对移动相机下动态物体的运动特性仍缺乏清晰理解。为提升性能，需结合物理层面的3D形状与动态特性来减少干扰。本文提出鲁棒方法V3D-SLAM，通过两个轻量级重评估阶段：首先利用空间推理的霍夫投票机制识别潜在移动和静态物体；其次通过切比雪夫距离作为相似性度量，检测由物体内部运动引起的动态噪声并精修静态点云。在包含真实相机轨迹的TUM RGB-D动态序列基准测试中，该方法超越最新SOTA SLAM方法。源代码已开源：https://github.com/tuantdang/v3d-slam。
原文摘要 · Abstract (English)
Simultaneous localization and mapping (SLAM) in highly dynamic environments is challenging due to the correlation complexity between moving objects and the camera pose. Many methods have been proposed to deal with this problem; however, the moving properties of dynamic objects with a moving camera remain unclear. Therefore, to improve SLAM's performance, minimizing disruptive events of moving objects with a physical understanding of 3D shapes and dynamics of objects is needed. In this paper, we propose a robust method, V3D-SLAM, to remove moving objects via two lightweight re-evaluation stages, including identifying potentially moving and static objects using a spatial-reasoned Hough voting mechanism and refining static objects by detecting dynamic noise caused by intra-object motions using Chamfer distances as similarity measurements. Our experiment on the TUM RGB-D benchmark on dynamic sequences with ground-truth camera trajectories showed that our methods outperform the most recent state-of-the-art SLAM methods. Our source code is available at https://github.com/tuantdang/v3d-slam.
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。