Advances in robotics research

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Depth-hybrid speeded-up robust features (DH-SURF) for real-time RGB-D SLAM

  • Lee, Donghwa (Division of Computer & Communication Engineering, Daegu University) ;
  • Kim, Hyungjin (Urban Robotics Laboratory, Korea Advanced Institute of Science and Technology) ;
  • Jung, Sungwook (Urban Robotics Laboratory, Korea Advanced Institute of Science and Technology) ;
  • Myung, Hyun (Urban Robotics Laboratory, Korea Advanced Institute of Science and Technology)
  • Received : 2017.11.10
  • Accepted : 2017.12.22
  • Published : 2018.03.25
⟨ Previous Next ⟩

Abstract

This paper presents a novel feature detection algorithm called depth-hybrid speeded-up robust features (DH-SURF) augmented by depth information in the speeded-up robust features (SURF) algorithm. In the keypoint detection part of classical SURF, the standard deviation of the Gaussian kernel is varied for its scale-invariance property, resulting in increased computational complexity. We propose a keypoint detection method with less variation of the standard deviation by using depth data from a red-green-blue depth (RGB-D) sensor. Our approach maintains a scale-invariance property while reducing computation time. An RGB-D simultaneous localization and mapping (SLAM) system uses a feature extraction method and depth data concurrently; thus, the system is well-suited for showing the performance of the DH-SURF method. DH-SURF was implemented on a central processing unit (CPU) and a graphics processing unit (GPU), respectively, and was validated through the real-time RGB-D SLAM.

Keywords

Acknowledgement

Grant : Development of robot intelligence technology for mobility with learning capability toward robust and seamless indoor and outdoor autonomous navigation

Supported by : Ministry of Trade, industry & Energy (MOTIE)

References

  1. Bay, H., Ess, A., Tuytelaars, T. and Van Gool, L. (2008), "Speeded-up robust features (SURF)", Comput. Vis. Image Und., 110(3), 346-359. https://doi.org/10.1016/j.cviu.2007.09.014
  2. Chen, X. and Jia, Y. (2014), "Indoor localization for mobile robots using lampshade corners as landmarks: Visual system calibration, feature extraction and experiments", J. Control Autom., 12(6), 1313-1322. https://doi.org/10.1007/s12555-013-0076-y
  3. Endres, F., Hess, J., Engelhard, N., Sturm, J., Cremers, D. and Burgard, W. (2012), "An evaluation of the RGB-D SLAM system", Proceeding of the 2012 IEEE International Conference on Robotics and Automation (ICRA), St. Paul, Minnesota, U.S.A., May.
  4. Fischler, M.A. and Bolles, R.C. (1981), "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography", Commun. ACM, 24(6), 381-395. https://doi.org/10.1145/358669.358692
  5. Havangi, R., Nekoui, M.A. and Teshnehlab, M. (2014), "An optimization based method for simultaneous localization and mapping", J. Control Autom., 12(4), 823-832. https://doi.org/10.1007/s12555-012-9503-8
  6. Henry, P., Krainin, M., Herbst, E., Ren, X. and Fox, D. (2012), "RGB-D mapping: Using kinect-style depth cameras for dense 3D modeling of indoor environments", J. Robot. Res., 31(5), 647-663. https://doi.org/10.1177/0278364911434148
  7. Kaess, M., Ranganathan, A. and Dellaert, F. (2008), "iSAM: Incremental smoothing and mapping", IEEE T. Robot., 24(6), 1365-1378. https://doi.org/10.1109/TRO.2008.2006706
  8. Khoshelham, K. and Elberink, S.O. (2012), "Accuracy and resolution of kinect depth data for indoor mapping applications", Sensors, 12(2), 1437-1454. https://doi.org/10.3390/s120201437
  9. Kim, H., Lee, D., Oh, T., Lee, S.W., Choe, Y. and Myung, H. (2013), "Feature based 6-DoF camera localization using prior point cloud and images", Proceeding of the 2nd International Conference on Robot Intelligence Technology and Applications (RiTA), Denver, Colorado, U.S.A., December.
  10. Kim, H., Oh, T., Lee, D. and Myung, H. (2014), "Image-based localization using prior map database and Monte Carlo localization", Proceeding of the 11th Ubiquitous Robots and Ambient Intelligence (URAI), Kuala Lumpur, Malaysia, November.
  11. Lee, D. and Myung, H. (2014), "Solution to the SLAM problem in low dynamic environments using a pose graph and an RGB-D sensor", Sensors, 14(7), 12467-12496. https://doi.org/10.3390/s140712467
  12. Lee, D., Kim, H. and Myung, H. (2012a), "2D image feature-based real-time RGB-D 3D SLAM", Proceeding of the 1st International Conference on Robot Intelligence Technology and Applications (RiTA), Gwangju, Korea, December.
  13. Lee, D., Kim, H. and Myung, H. (2012b), "GPU-based real-time RGB-D 3D SLAM", Proceeding of the 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Daejeon, Korea, November.
  14. Lee, S. and Oh, P.Y. (2015), "Sensor information analysis for a humanoid robot", J. Control Autom., 13(1), 175-181. https://doi.org/10.1007/s12555-013-0519-5
  15. Lowe, D.G. (2004), "Distinctive image features from scale-invariant keypoints", J. Comput. Vision, 60(2), 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  16. Park, S. and Park, S.K. (2014), "Global localization for mobile robots using reference scan matching", J. Control Autom., 12(1), 156-168. https://doi.org/10.1007/s12555-012-9223-0
  17. Pioneer3-AT (2015), .
  18. Scaramuzza, D. and Fraundorfer, F. (2011), "Visual odometry [Tutorial]", IEEE Robot. Autom. Magazine, 18(4), 80-92. https://doi.org/10.1109/MRA.2011.943233
  19. Sethian, J.A. (1996), "A fast marching level set method for monotonically advancing fronts", Pro. Nat. Acad. Sci., 93(4), 1591-1595. https://doi.org/10.1073/pnas.93.4.1591
  20. Szeliski, R. (2010), Computer Vision: Algorithms and Applications, Springer-Verlag New York, New York, U.S.A.
  21. Telea, A. (2004), "An image inpainting technique based on the fast marching method", J. Graph. Tools, 9(1), 23-34. https://doi.org/10.1080/10867651.2004.10487596
  22. Zhang, Z. (2012), "Microsoft kinect sensor and its effect", IEEE Multimedia, 19(2), 4-10. https://doi.org/10.1109/MMUL.2012.24