Improved ICP-based Pose Estimation by Distance-aware 3D Mapping

Hani Javan Hemmat, Egor Bondarev, Gijs Dubbelman, Peter H. N. de With

2014

Abstract

In this paper, we propose and evaluate various distance-aware weighting strategies to increase the accuracy of pose estimation by improving the accuracy of a voxel-based model, generated from the data obtained by low-cost depth sensors. We investigate two strategies: (a) weight definition to prioritize prominence of the sensed data according to the data accuracy, and (b) model updating to determine the influential level of the newly captured data on the existing synthetic 3D model. Specifically, we propose Distance-Aware (DA) and Distance-Aware Slow-Saturation (DASS) updating methods to intelligently integrate the depth data into the 3D model, according to the distance-sensitivity metric of a low-cost depth sensor. We validate the proposed methods by applying them to a benchmark of datasets and comparing the resulting pose trajectories to the corresponding ground-truth. The obtained improvements are measured in terms of Absolute Trajectory Error (ATE) and Relative Pose Error (RPE) and compared against the performance of the original Kinfu. The validation shows that on the average, our most promising method called DASS, leads to a pose estimation improvement in terms of ATE and RPE by 43.40% and 48.29%, respectively. The method shows robust performance for all datasets, with best-case improvement reaching 90% of pose-error reduction.

References

  1. Andersen, V., Aans, H., and Brentzen, J. A. (2010). Surfel based geometry reconstruction. In Collomosse, J. P. and Grimstead, I. J., editors, Theory and Practice of Computer Graphics, Sheffield, United Kingdom, 2010. Proceedings, pages 39-44.
  2. Besl, P. and McKay, N. (1992). A method for registration of 3-d shapes. IEEE Transaction on Pattern Analysis and Machine Intelligence, 14(2):239-256.
  3. Bondarev, E., Heredia, F., Favier, R., Ma, L., and de With, P. H. N. (2013). On photo-realistic 3D reconstruction of large-scale and arbitrary-shaped environments. In CCNC, pages 621-624.
  4. Bylow, E., Sturm, J., Kerl, C., Kahl, F., and Cremers, D. (2013). Real-time camera tracking and 3D reconstruction using signed distance functions. In Proceedings of Robotics: Science and Systems, Berlin, Germany.
  5. Chang, J. Y., Park, H., Park, I. K., Lee, K. M., and Lee, S. U. (2011). Gpu-friendly multi-view stereo reconstruction using surfel representation and graph cuts. Comput. Vis. Image Underst., 115(5):620-634.
  6. Chow, J., Ang, K., Lichti, D., and Teskey, W. (2012). Performance analysis of a low-cost triangulation-based 3d camera: Microsoft kinect system. In ISPRS12, pages XXXIX-B5:175-180.
  7. Curless, B. and Levoy, M. (1996). A volumetric method for building complex models from range images. In ACM SIGGRAPH Conference Proceedings. ACM.
  8. Endres, F., Hess, J., Engelhard, N., Sturm, J., Cremers, D., and Burgard, W. (2012). An evaluation of the rgbd slam system. In Robotics and Automation (ICRA), 2012 IEEE Int. Conf. on, pages 1691-1696. IEEE.
  9. Engelhard, N., Endres, F., Hess, J., Sturm, J., and Burgard, W. (2011). Real-time 3D visual slam with a hand-held camera. In Proc. of the RGB-D Workshop on 3D Perception in Robotics at the European Robotics Forum, Vasteras, Sweden.
  10. Henry, P., Krainin, M., Herbst, E., Ren, X., and Fox, D. (2010). Rgb-d mapping: Using depth cameras for dense 3D modeling of indoor environments. the 12th Int. Symposium on Experimental Robotics (ISER).
  11. 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. Int. Journ. Robotics Research, 31(5):647-663.
  12. Hornung, A., Wurm, K. M., Bennewitz, M., Stachniss, C., and Burgard, W. (2013). OctoMap: An efficient probabilistic 3D mapping framework based on octrees. Autonomous Robots.
  13. Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., and Fitzgibbon, A. (2011). Kinectfusion: real-time 3D reconstruction and interaction using a moving depth camera. In Proc. 24th annual ACM Symp. User interface software and technology, UIST 7811, pages 559-568, New York, NY, USA. ACM.
  14. Khoshelham, K. (2011). Accuracy analysis of kinect depth data. ISPRS Workshop Laser Scanning, 38:1.
  15. Khoshelham, K. and Elberink, S. O. (2012). Accuracy and resolution of kinect depth data for indoor mapping applications. Sensors, 12(2):1437-1454.
  16. Kubacki, D. B., Bui, H. Q., Babacan, S. D., and Do, M. N. (2012). Registration and integration of multiple depth images using signed distance function.
  17. Kümmerle, R., Grisetti, G., Strasdat, H., Konolige, K., and Burgard, W. (2011). g2o: A general framework for graph optimization. In Robotics and Automation (ICRA), IEEE Int. Conf. on, pages 3607-3613. IEEE.
  18. Newcombe, R. A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohli, P., Shotton, J., Hodges, S., and Fitzgibbon, A. (2011a). Kinectfusion: Realtime dense surface mapping and tracking. In Proceeding of 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 7811, pages 127-136, Washington, DC, USA. IEEE Computer Society.
  19. Newcombe, R. A., Lovegrove, S., and Davison, A. J. (2011b). Dtam: Dense tracking and mapping in realtime. In Metaxas, D. N., Quan, L., Sanfeliu, A., and Gool, L. J. V., editors, ICCV, pages 2320-2327. IEEE.
  20. PCL (2011). Kinectfusion implementation in the PCL. http://svn.pointclouds.org/pcl/trunk/.
  21. Ren, C. Y. and Reid, I. (2012). A unified energy minimization framework for model fitting in depth. In Computer Vision-ECCV 2012. Workshops and Demonstrations, pages 72-82. Springer.
  22. Rusu, R. B. and Cousins, S. (2011). 3D is here: Point Cloud Library (PCL). In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China.
  23. Sturm, J., Engelhard, N., Endres, F., Burgard, W., and Cremers, D. (2012). A benchmark for the evaluation of rgb-d slam systems. In Intelligent Robots and Systems (IROS), IEEE/RSJ Int. Conf. on, pages 573-580.
  24. Whelan, T., Johannsson, H., Kaess, M., Leonard, J. J., and McDonald, J. (2013). Robust real-time visual odometry for dense rgb-d mapping. In IEEE International Conference on Robotics and Automation, ICRA.
  25. Whelan, T., Kaess, M., Fallon, M., Johannsson, H., Leonard, J., and McDonald, J. (2012). Kintinuous: Spatially extended KinectFusion. In RSS Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Sydney, Australia.
  26. Zeng, M., Zhao, F., Zheng, J., and Liu, X. (2012). A memory-efficient kinectfusion using octree. In Proceedings of the First international conference on Computational Visual Media, CVM'12, pages 234- 241, Berlin, Heidelberg. Springer-Verlag.
Download


Paper Citation


in Harvard Style

Javan Hemmat H., Bondarev E., Dubbelman G. and de With P. (2014). Improved ICP-based Pose Estimation by Distance-aware 3D Mapping . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 360-367. DOI: 10.5220/0004716403600367


in Bibtex Style

@conference{visapp14,
author={Hani Javan Hemmat and Egor Bondarev and Gijs Dubbelman and Peter H. N. de With},
title={Improved ICP-based Pose Estimation by Distance-aware 3D Mapping},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={360-367},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004716403600367},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Improved ICP-based Pose Estimation by Distance-aware 3D Mapping
SN - 978-989-758-009-3
AU - Javan Hemmat H.
AU - Bondarev E.
AU - Dubbelman G.
AU - de With P.
PY - 2014
SP - 360
EP - 367
DO - 10.5220/0004716403600367