Modeling of Environment for Technical Vision: Automatic Detection of Dynamic Objects in the Data Stream

The article describes the implemented package in the ROS framework, which creates a new data stream of the depth camera without a dynamic object. This product can be used in computer vision systems to cut objects that can move on the map in the data stream, thereby preventing the systems from focusing on unnecessary objects. As an example of use, the task of the SLAM method was implemented using data from the Microsoft Kinect 2.0 sensor and building a map for localizing the robot in RTAB-Map.

[1]  Wei Wang,et al.  Robust Place Recognition and Loop Closing in Laser-Based SLAM for UGVs in Urban Environments , 2018, IEEE Sensors Journal.

[2]  Elise Lachat,et al.  Assessment and Calibration of a RGB-D Camera (Kinect v2 Sensor) Towards a Potential Use for Close-Range 3D Modeling , 2015, Remote. Sens..

[3]  Zhengyou Zhang,et al.  Microsoft Kinect Sensor and Its Effect , 2012, IEEE Multim..

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

[5]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[6]  Rong Xiong,et al.  A framework for multi-session RGBD SLAM in low dynamic workspace environment , 2016, CAAI Trans. Intell. Technol..

[7]  Pileun Kim,et al.  SLAM-driven robotic mapping and registration of 3D point clouds , 2018 .

[8]  James R. Bergen,et al.  Visual odometry , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[9]  Bin Shao,et al.  3D Indoor Environment Modeling and Detection of Moving Object and Scene Understanding , 2018, Trans. Edutainment.

[10]  Wolfram Burgard,et al.  3-D Mapping With an RGB-D Camera , 2014, IEEE Transactions on Robotics.

[11]  Ezzeddine Zagrouba,et al.  Dense 3D SLAM in Dynamic Scenes Using Kinect , 2015, IbPRIA.

[12]  Wolfram Burgard,et al.  Map building with mobile robots in dynamic environments , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[13]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[14]  Javier Civera,et al.  Camera self-calibration for sequential Bayesian structure from motion , 2009, 2009 IEEE International Conference on Robotics and Automation.

[15]  Ezzeddine Zagrouba,et al.  3D modeling of indoor environments using Kinect sensor , 2013, 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013).

[16]  John J. Leonard,et al.  Dynamic pose graph SLAM: Long-term mapping in low dynamic environments , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Paul Newman,et al.  Appearance-only SLAM at large scale with FAB-MAP 2.0 , 2011, Int. J. Robotics Res..