A Robust SLAM towards Dynamic Scenes Involving Non-rigid Objects

SLAM has achieved great progress over the past decades. Typical SLAM algorithms are based on the assumption that the observed environments are static. The strong assumption limits the use of visual SLAM systems in real-world scenes. In this paper, we propose a robust SLAM towards dynamic scenes involving non-rigid objects. We carry out instance segmentation to detect objects and refine the tracking by additionally extract static regions from non-rigid potential dynamic objects. Our method is evaluated on TUM RGB-D dataset. Experiments show that the proposed SLAM performs well in dynamic environments.

[1]  Jitendra Malik,et al.  Learning to segment moving objects in videos , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[3]  Qi Wei,et al.  DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.

[6]  U SaputraMuhamad Risqi,et al.  Visual SLAM and Structure from Motion in Dynamic Environments , 2018 .

[7]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[8]  Javier Civera,et al.  DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes , 2018, IEEE Robotics and Automation Letters.

[9]  Tsung-Han Lin,et al.  Deep learning of spatio-temporal features with geometric-based moving point detection for motion segmentation , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[11]  K. Madhava Krishna,et al.  Moving object detection by multi-view geometric techniques from a single camera mounted robot , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Peter Cheeseman,et al.  On the Representation and Estimation of Spatial Uncertainty , 1986 .

[14]  Hujun Bao,et al.  Robust monocular SLAM in dynamic environments , 2013, 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).

[15]  Wolfram Burgard,et al.  Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters , 2007, IEEE Transactions on Robotics.

[16]  Hugh F. Durrant-Whyte.  Uncertain geometry in robotics , 1988, IEEE J. Robotics Autom..

[17]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[18]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[19]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[20]  Dieter Fox,et al.  RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments , 2012, Int. J. Robotics Res..

[21]  Guy Le Besnerais,et al.  Moving Object Detection in Real-Time Using Stereo from a Mobile Platform , 2015, Unmanned Syst..