DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes

被引:854
作者
Bescos, Berta [1 ]
Facil, Jose M. [1 ]
Civera, Javier [1 ]
Neira, Jose [1 ]
机构
[1] Univ Zaragoza, I3A, Zaragoza 50018, Spain
关键词
SLAM; visual-based navigation; localization; SLAM;
D O I
10.1109/LRA.2018.2860039
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service robotics or autonomous vehicles. In this letter we present DynaSLAM, a visual SLAM system that, building on ORB-SLAM2, adds the capabilities of dynamic object detection and background inpainting. DynaSLAM is robust in dynamic scenarios for monocular, stereo, and RGB-D configurations. We are capable of detecting the moving objects either by multiview geometry, deep learning, or both. Having a static map of the scene allows inpainting the frame background that has been occluded by such dynamic objects. We evaluate our system in public monocular, stereo, and RGB-D datasets. We study the impact of several accuracy/speed trade-offs to assess the limits of the proposed methodology. DynaSLAM outperforms the accuracy of standard visual SLAM baselines in highly dynamic scenarios. And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.
引用
收藏
页码:4076 / 4083
页数:8
相关论文
共 24 条
[1]  
Alcantarilla PF, 2012, IEEE INT CONF ROBOT, P1290, DOI 10.1109/ICRA.2012.6224690
[2]  
Ambrus R., 2016, P IEEE RAS 16 INT C
[3]  
Concha A, 2015, IEEE INT C INT ROBOT, P5686, DOI 10.1109/IROS.2015.7354184
[4]   Direct Sparse Odometry [J].
Engel, Jakob ;
Koltun, Vladlen ;
Cremers, Daniel .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (03) :611-625
[5]   LSD-SLAM: Large-Scale Direct Monocular SLAM [J].
Engel, Jakob ;
Schoeps, Thomas ;
Cremers, Daniel .
COMPUTER VISION - ECCV 2014, PT II, 2014, 8690 :834-849
[6]   Vision meets robotics: The KITTI dataset [J].
Geiger, A. ;
Lenz, P. ;
Stiller, C. ;
Urtasun, R. .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2013, 32 (11) :1231-1237
[7]   Evaluation of the potential of automatic segmentation of the mandibular canal using cone-beam computed tomography [J].
Gerlach, Nicolaas Lucius ;
Meijer, Gerrit Jacobus ;
Kroon, Dirk-Jan ;
Bronkhorst, Ewald Maria ;
Berge, Stefaan Jozef ;
Maal, Thomas Jan Jaap .
BRITISH JOURNAL OF ORAL & MAXILLOFACIAL SURGERY, 2014, 52 (09) :838-844
[8]  
Graber G., 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), P708, DOI 10.1109/ICCVW.2011.6130318
[9]  
He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]
[10]   Effective Background Model-Based RGB-D Dense Visual Odometry in a Dynamic Environment [J].
Kim, Deok-Hwa ;
Kim, Jong-Hwan .
IEEE TRANSACTIONS ON ROBOTICS, 2016, 32 (06) :1565-1573