Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Image Feature-Based Real-Time RGB-D 3D SLAM with GPU Acceleration

GPU 가속화를 통한 이미지 특징점 기반 RGB-D 3차원 SLAM

  • Lee, Donghwa (Dept. of Civil and Environmental Engineering, KAIST) ;
  • Kim, Hyongjin (Dept. of Civil and Environmental Engineering, KAIST) ;
  • Myung, Hyun (Dept. of Civil and Environmental Engineering, KAIST)
  • 이동화 (KAIST 건설 및 환경공학과) ;
  • 김형진 (KAIST 건설 및 환경공학과) ;
  • 명현 (KAIST 건설 및 환경공학과)
  • Received : 2013.02.28
  • Accepted : 2013.04.02
  • Published : 2013.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes an image feature-based real-time RGB-D (Red-Green-Blue Depth) 3D SLAM (Simultaneous Localization and Mapping) system. RGB-D data from Kinect style sensors contain a 2D image and per-pixel depth information. 6-DOF (Degree-of-Freedom) visual odometry is obtained through the 3D-RANSAC (RANdom SAmple Consensus) algorithm with 2D image features and depth data. For speed up extraction of features, parallel computation is performed with GPU acceleration. After a feature manager detects a loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and builds a 3D point cloud based map.

Keywords

References

  1. M. W. M. G.Dissanayake, P. Newman, S. Clark, H. F. Durrant-Whyte, and M. Csorba, "A solution to the simultaneous localization and map building (SLAM) problem," Robotics and Automation, IEEE Transactions on, vol. 17, no. 3, pp. 229-241, Jun. 2001. https://doi.org/10.1109/70.938381
  2. D. Hahnel, W. Burgard, D. Fox, and S. Thrun, "An efficient FastSLAM algorithm for generatingmaps of large-scale cyclic environments from raw laser range measurements," Proc. Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 2003 IEEE/RSJ International Conference on, pp. 206-211, Oct. 2003.
  3. M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges," Proc.of the18th International Joint Conference on Artificial Intelligence, pp. 1151-1156, 2003.
  4. S.-Y. Hwang and J.-B. Song, "Monocular vision and odometry-based SLAM using position and orientation of ceiling lamps," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 17, no. 2, pp. 164-170, Feb. 2011. https://doi.org/10.5302/J.ICROS.2011.17.2.164
  5. K.-Y. Yoon, S.-W. Choi, and C.-H. Lee, "An approach for localization around indoor corridors based on visual attention model," Journal of Institute of Control, Robotics and Systems (inKorean), vol. 17, no. 2, pp. 93-101, Feb. 2011. https://doi.org/10.5302/J.ICROS.2011.17.2.093
  6. M. Kaess, A. Ranganathan, and F. Dellaert, "iSAM: Incremental smoothing and mapping," Robotics, IEEE Transactions on, vol. 24, no. 6, pp. 1365-1378, Dec. 2008. https://doi.org/10.1109/TRO.2008.2006706
  7. A. S. Huang, A. Bachrach, P. Henry, M. Krainin, D. Maturana, D. Fox, and N. Roy, "Visual odometry and mapping for autonomous flightusing an RGB-Dcamera," Proc. of The 15th International Symposium on Robotics Research(ISRR), 2011.
  8. R.Kummerle, G. Grisetti, H. Strasdat, K. Konolige, and W.Burgard, "g2o: A general framework for graph optimization," Robotics and Automation (ICRA), 2011 IEEE International Conference on, pp. 3607-3613, May 2011.
  9. J. Sturm, N. Engelhard, F. Endres, W. Burgard, and D. Cremers, "A benchmark for the evaluation of RGB-D SLAMsystems," Proc. Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, pp. 573-580, Oct. 2012.
  10. F. Endres, J. Hess, N. Engelhard, J. Sturm, D. Cremers, and W. Burgard, "An evaluation of theRGB-D SLAM system," Proc. Robotics and Automation (ICRA), 2012 IEEE International Conference on, pp. 1691-1696, May 2012.
  11. N. Engelhard, F. Endres, J. Hess, J. Sturm, and W. Burgard, "Real-time 3D visual SLAMwith a hand-held RGB-D camera," Proc. of the RGB-D Workshop on 3D Perception inRobotics at the European Robotics Forum, Vasteras, Sweden, 2011.
  12. P. Henry, M. Krainin, E. Herbst, X. Ren, and D. Fox, "RGB-D mapping: Using Kinect-styledepth cameras for dense 3D modeling of indoor environments," The International Journal of Robotics Research, vol. 31, no. 5, pp. 647-663, Apr. 2012. https://doi.org/10.1177/0278364911434148
  13. D. Lee, H. Kim, and H.Myung, "Real-time RGB-D 3D SLAM with GPU acceleration," Proc. of Daejeon & Chungcheong Regional Conferenceof Institute of Control, Robotics and Systems (in Korean), pp. 179-182, Dec. 2012.
  14. D. Lee, H.Kim, and H. Myung, "2D image feature-based real-time RGB-D 3D SLAM," Proc. of International Conference on Robot Intelligence Technology and Applications 2012 (RiTA 2012), pp. 485-492, Gwangju, Korea, Dec. 2012.
  15. D. Lee, H.Kim, and H.Myung, "GPU-based real-time RGB-D 3D SLAM," Proc. of International Conference on Ubiquitous Robots and Ambient Intelligence 2012 (URAI 2012), pp. 46-48, Daejeon, Korea, Nov. 26-29, 2012.
  16. Z. Zhang, "Microsoft Kinect sensor and its effect," IEEE Multimedia,vol. 19, no. 2, pp. 4-10, 2012.
  17. S.Thrun and M. Montemerlo, "The GraphSLAM algorithm with applications to large-scale mapping of urban structures,"The International Journal of Robotics Research, vol. 25, no. 5-6, pp. 403-429, May-Jun. 2006. https://doi.org/10.1177/0278364906065387
  18. OpenCV (Open source Computer Vision): http://opencv.org/
  19. PCL (Point Cloud Library): http://pointclouds.org/

Cited by

  1. Localization of a Monocular Camera using a Feature-based Probabilistic Map vol.21, pp.4, 2015, https://doi.org/10.5302/J.ICROS.2015.14.8035
  2. 3D Omni-directional Vision SLAM using a Fisheye Lens Laser Scanner vol.21, pp.7, 2015, https://doi.org/10.5302/J.ICROS.2015.15.0002
  3. Obstacle Detection Algorithm Using Forward-Viewing Mono Camera vol.21, pp.9, 2015, https://doi.org/10.5302/J.ICROS.2015.15.0104