Robust and Efficient RGB-D SLAM in Dynamic Environments

被引:22
作者
Yang, Xin [1 ]
Yuan, Zikang [1 ]
Zhu, Dongfu [1 ]
Chi, Cheng [1 ]
Li, Kun [1 ]
Liao, Chunyuan [2 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China
[2] HiScene Informat Technol Co Ltd, Shanghai 201210, Peoples R China
基金
中国国家自然科学基金;
关键词
Dynamics; Simultaneous localization and mapping; Cameras; Three-dimensional displays; Pose estimation; Robustness; Motion segmentation; Robotics and automation; robots; robot sensing systems; simultaneous localization and mapping; DEPTH PREDICTION; ALGORITHM; OPTIMIZATION;
D O I
10.1109/TMM.2020.3038323
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.(1) (1) A demo video is provided on https://github.com/cc-qy/Dynamic-RGB-D-SLAM
引用
收藏
页码:4208 / 4219
页数:12
相关论文
共 30 条
[1]  
Azartash Haleh, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), P1280, DOI 10.1109/ICASSP.2014.6853803
[2]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[3]   The Quickhull algorithm for convex hulls [J].
Barber, CB ;
Dobkin, DP ;
Huhdanpaa, H .
ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 1996, 22 (04) :469-483
[4]   DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes [J].
Bescos, Berta ;
Facil, Jose M. ;
Civera, Javier ;
Neira, Jose .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04) :4076-4083
[5]   A METHOD FOR REGISTRATION OF 3-D SHAPES [J].
BESL, PJ ;
MCKAY, ND .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :239-256
[6]   DENAO: Monocular Depth Estimation Network With Auxiliary Optical Flow [J].
Chen, Jingyu ;
Yang, Xin ;
Jia, Qizeng ;
Liao, Chunyuan .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (08) :2598-2610
[7]   CaMap: Camera-based Map Manipulation on Mobile Devices [J].
Chen, Liang ;
Chen, Dongyi .
PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND APPLICATION ENGINEERING (CSAE2018), 2018,
[8]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[9]  
Dai W., 2018, ARXIV181103217
[10]   Efficient graph-based image segmentation [J].
Felzenszwalb, PF ;
Huttenlocher, DP .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 59 (02) :167-181