Robust and Efficient RGB-D SLAM in Dynamic Environments
Robust and Efficient RGB-D SLAM in Dynamic Environments
复制标题
动态环境中稳健且高效的 RGB-D SLAM
DOI：
10.1109/tmm.2020.3038323
复制
发表时间：
2021
影响因子：
7.3
通讯作者：
Liao Chunyuan
中科院分区：
文献类型：
--
作者：
Yang Xin;Yuan Zikang;Zhu Dongfu;Chi Cheng;Li Kun;Liao Chunyuan
使用RGB-D相机的同时定位和映射（SLAM）是许多增强现实（AR）应用的关键使能技术。然而，大多数现有的RGB-D SLAM方法在动态场景中可能由于移动对象引起的非平凡姿态估计误差而失败。在这项研究中，我们提出了一个准确和强大的RGB-D SLAM系统的动态场景，可以运行在一个单一的双核CPU实时。我们的系统的核心是一个强大的和有效的动态关键点排除方法，它包括三个步骤：1）分组空间和外观相关的像素的关键帧到区域; 2）识别动态区域，通过检查运动的一致性，在每个区域中的关键点; 3）排除关键点在所识别的动态区域以及匹配点在3D局部地图。动态关键点排除方法可以很容易地集成到任何基于关键点的RGB-D SLAM系统中，以提高动态场景中的准确性和鲁棒性，而时间增加很小（每帧16.6ms）。在TUM数据集上的实验结果表明，我们在Intel i7-4900 CPU上运行的方法甚至比在P4000 GPU和类似CPU上并行运行的最先进方法DS-SLAM [1]快2.3倍。此外，我们的系统在更小的绝对轨迹误差（ATE）方面优于最先进的方法[1]-[4]。我们还将我们的系统应用于真实的AR应用，并使用手持式RGB-D相机进行了现场实验，证明了我们的方法在实际应用中的鲁棒性和通用性。11 https://github.com/cc-qy/Dynamic-RGB-D-SLAM上提供了演示视频
Simultaneous localization and mapping (SLAM) using an RGB-D camera is a key enabling technique for many augmented reality (AR) applications. However, most existing RGB-D SLAM methods could fail in dynamic scenarios due to non-trivial pose estimation errors arising from moving objects. In this study, we present an accurate and robust RGB-D SLAM system for dynamic scenarios which can run real-time on a single dual-core CPU. The core of our system is a robust and efficient dynamic keypoint exclusion method which consists of three steps: 1) grouping spatially and appearance related pixels of a keyframe into regions; 2) identifying dynamic regions by checking motion consistency of keypoints in every region; 3) excluding keypoints in the identified dynamic regions as well as the matching points in the 3D local map. The dynamic keypoint exclusion method can be easily integrated into any keypoint based RGB-D SLAM system for improving the accuracy and robustness in dynamic scenes with trivial time increase (16.6ms per frame). Experimental results on the TUM dataset demonstrates that our method which runs on an Intel i7-4900 CPU is even 2.3X faster than the state-of-the-art method DS-SLAM [1] which runs parallel on a P4000 GPU and a comparable CPU. In addition, our system outperforms the state-of-the-art methods [1]–[4] in terms of smaller absolute trajectory errors (ATE). We also apply our system to a real AR application and live experiments with a hand-held RGB-D camera demonstrate the robustness and generalizability of our method in practical scenarios.11A demo video is provided on https://github.com/cc-qy/Dynamic-RGB-D-SLAM