Skip to main content
SpringerLink
Log in

Frequency-based underwater terrain segmentation

  • Published:
Autonomous Robots Aims and scope Submit manuscript

Abstract

A method for segmenting three-dimensional data of underwater unstructured terrains is presented. The three-dimensional point clouds are converted to two-dimensional elevation maps and analyzed for segmentation in the frequency domain. The lower frequency components represent the slower varying undulations of the underlying ground. The cut-off frequency, below which the frequency components form the ground surface, is determined automatically using peak detection. The user can also specify a maximum admissible size of objects to drive the automatic detection of the cut-off frequency. The points above the estimated ground surface are clustered via standard proximity clustering to form object segments. The precision of the segmentation is compared against ground truth hand labelled data acquired by a stereo camera pair and a structured light sensor. It is also evaluated for registration error when the extracted segments are used for sub-map alignment. The proposed approach is compared to three point cloud based and two image based segmentation algorithms. The results show that the approach is applicable to a range of different terrains and is able to generate features useful for navigation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. A video illustrating the results presented in this work is available at http://youtu.be/n0F42jliKdY

  2. We use the term “ground” as opposed to seafloor to stay close to the terminology used in the ground robotics community. Furthermore, the notion of ground surface as used in this paper is to be understood as the background terrain undulations.

  3. In this text we form objects only from the points above the separation layer. However, objects can similarly be formed from points below this layer.

  4. Available for download from the author web site: https://sites.google.com/site/wwwjingyuan.

References

  • Besl, P. J., & McKay, H. D. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 14(2), 239–256.

    Article  Google Scholar 

  • Bogdan Rusu, R., & Cousins, S. (2011). 3D is here: Point cloud library (PCL). In IEEE international conference on Robotics and automation (ICRA). Shanghai, China (May 9–13, 2011).

  • Borrmann, D., Elseberg, J., Lingemann, K., Nüchter, A., & Hertzberg, J. (2008). Globally consistent 3d mapping with scan matching. Robotics and Autonomous Systems, 56(2), 130–142.

    Article  Google Scholar 

  • Boykov, Y., & Funka-Lea, G. (2006). Graph cuts and efficient and image segmentation. International Journal of Computer Vision, 70(2), 109–131.

    Article  Google Scholar 

  • Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools, 25(11), 120.

    Google Scholar 

  • Brown, C. J., Smith, S. J., Lawton, P., & Anderson, J. T. (2011). Benthic habitat mapping: A review of progress towards improved understanding of the spatial ecology of the seafloor using acoustic techniques. Estuarine Coastal and Shelf Science, 92, 502–520.

    Article  Google Scholar 

  • Chen, X., Golovinskiy, A., & Funkhouser, T. (2009). A benchmark for 3d mesh segmentation. ACM Transactions on Graphics (TOG), 28(3), 73.

    Article  Google Scholar 

  • Douillard, B., Nourani-Vatani, N., Johnson-Roberson, M., Williams, S., Roman, C., Pizarro, O., Vaughn, I., & Inglis, G. (2012a). FFT-based terrain segmentation for underwater mapping. In Robotics: Science and Systems (RSS), Sydney, Australia.

  • Douillard, B., Quadros, A., Morton, P., Underwood, J. P., Deuge, M. D., & Hugosson, S., et al. (2012b). Scan segments matching for pairwise 3D alignment. In IEEE International Conference on Robotics and Automation (ICRA).

  • Douillard, B., Underwood, J., Kuntz, N., Vlaskine, V., Quadros, A., & Morton, P., et al. (2010). On the segmentation of 3D LIDAR point clouds. In IEEE International Conference on Robotics and Automation (ICRA).

  • Felzenszwalb, P., & Huttenlocher, D. H. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2), 167–181.

    Article  Google Scholar 

  • Geiger, A., Roser, M., & Urtasun, R. (2010). Efficient large-scale stereo matching. In Asian Conference on Computer Vision. Queenstown, New Zealand (November 2010).

  • Golovinskiy, A., & Funkhouser, T. (2009). Min-cut based segmentation of point clouds. In IEEE Internationa Conference on Computer Vision (ICCV) Workshops (pp. 39–46).

  • Hirschmuller, H. (2008). Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 328–341.

    Article  Google Scholar 

  • Horn, B. (1986). Robot vision. Cambridge: The MIT Press.

    Google Scholar 

  • Kalogerakis, E., Hertzmann, A., & Singh, K. (2010). Learning 3d mesh segmentation and labeling. ACM Transactions on Graphics (TOG), 29(4), 102.

    Article  Google Scholar 

  • Kolmogorov, V., & Zabih, R. (2001). Computing visual correspondence with occlusions using graph cuts. In Computer Vision, 2001. ICCV 2001. Proceedings 8th IEEE International Conference on (Vol. 2, pp. 508–515).

  • Kunis, S. (2006). Nonequispaced FFT - Generalisation and Inversion. Ph.D. thesis, Germany: Universität Lübeck.

  • Pauling, F., Bosse, M., & Zlot, R. (2009). Automatic segmentation of 3D laser point clouds by ellipsoidal region growing. In Australasian Conference on Robotics and Automation (ACRA).

  • Petillot, Y., Ruiz, I., & Lane, D. (2001). Underwater vehicle obstacle avoidance and path planning using a multi-beam forward looking sonar. IEEE Journal of Oceanic Engineering, 26(2), 240–251.

    Google Scholar 

  • Proakis, J. G., & Manolakis, D. G. (1996). Digital signal processing—Principles, algorithms, and applications (3rd ed.). Englewood Cliffs: Prentice Hall International.

    Google Scholar 

  • Reed, S., Ruiz, I., Capus, C., & Petillot, Y. (2006). The fusion of large scale classified side-scan sonar image mosaics. IEEE Transactions on Image Processing, 15(7), 2049–2060.

    Article  Google Scholar 

  • Roman, C., Inglis, G., & Rutter, J. (2010). Application of structured light imaging for high resolution mapping of underwater archaeological sites. In IEEE OCEANS, Sydney (pp. 1–9).

  • Roman, C., & Singh, H. (2006). Consistency based error evaluation for deep sea bathymetric mapping with robotic vehicles. In IEEE International Conference on Robotics and Automation (ICRA) (pp. 3568–3574).

  • Roman, C., & Singh, H. (2007). A self-consistent bathymetric mapping algorithm. Journal of Field Robotics, 24(1–2), 23–50.

    Article  MATH  Google Scholar 

  • Salvi, J., Matabosch, C., Fofi, D., & Forest, J. (2007). A review of recent range image registration methods with accuracy evaluation. Image and Vision Computing, 25(5), 578–596.

    Article  Google Scholar 

  • Schoenberg, J., Nathan, A., & Campbell, M. (2010). Segmentation of dense range information in complex urban scenes. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

  • Seber, G. (1984). Multivariate observations (Vol. 41). New York: Wiley.

    Book  MATH  Google Scholar 

  • Segal, A., Haehnel, D., & Thrun, S. (2009). Generalized-icp. In Proc. of Robotics: Science and Systems (RSS) (Vol. 25, pp. 26–27).

  • Sheehan, M., Harrison, A., & Newman, P. (2010). Automatic self-calibration of a full field-of-view 3d n-laser scanner. In Proceedings of the International Symposium on Experimental, Robotics (pp. 1–14).

  • Steingrube, P., Gehrig, S., & Franke, U. (2009). Performance evaluation of stereo algorithms for automotive applications. In Computer vision systems (pp. 285–294).

  • Strom, J., Richardson, A., & Olson, E. (2010). Graph-based segmentation of colored 3d laser point clouds. In IEEE/RSJ International Conference on Intelligent Robots and Systems.

  • Triebel, R., Shin, J., & Siegwart, R. (2010). Segmentation and unsupervised part-based discovery of repetitive objects. In Robotics: Science and Systems, Zaragoza, Spain.

  • Williams, S., Pizarro, O., Jakuba, M., & Barrett, N. (2010). AUV benthic habitat mapping in South Eastern Tasmania. In Field and Service Robotics (pp. 275–284). Springer, Berlin.

  • Yuan, J., Egil Bae, X. C. T., & Boykov, Y. (2010). A continuous max-flow approach to Potts model. Computer Vision–ECCV, 6316, 379–392.

    Google Scholar 

  • Zhu, X., Zhao, H., Liu, Y., Zhao, Y., & Zha, H. (2010). Segmentation and classification of range image from an intelligent vehicle in urban environment. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 1457–1462).

Download references

Acknowledgments

This research was supported by the Australian Research Council (ARC) through the Discovery program (DP110101986), the Australian Government through the SIEF program, and by the Australian Centre for Field Robotics at the University of Sydney. The authors would like to thank Alastair Quadros, Peter Morton and Vsevolod Vlaskine for valuable help with software, as well as James P. Underwood, Mitch Bryson and Donald Danserau for useful discussions.

Author information

Authors and Affiliations

  1. Jet Propulsion Laboratory, M/S 198-235, 4800 Oak Grove Dr., Pasadena, CA, 91109, USA

    B. Douillard

  2. Australian Centre for Field Robotics, The University of Sydney, The Rose Street Building J04, Sydney, NSW, 2006, Australia

    N. Nourani-Vatani, O. Pizarro & S. Williams

  3. The Department of Naval Architecture and Marine Engineering, University of Michigan, Ann Arbor, MI, 48109, USA

    M. Johnson-Roberson

  4. Department of Ocean Engineering, The University of Rhode Island, Narragansett, RI, 02882, USA

    C. Roman & I. Vaughn

Authors
  1. B. Douillard
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. N. Nourani-Vatani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Johnson-Roberson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. O. Pizarro
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. S. Williams
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. C. Roman
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. I. Vaughn
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. Douillard.

Additional information

B. Douillard and N. Nourani-Vatani have contributed equally to this study.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Douillard, B., Nourani-Vatani, N., Johnson-Roberson, M. et al. Frequency-based underwater terrain segmentation. Auton Robot 35, 255–269 (2013). https://doi.org/10.1007/s10514-013-9353-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10514-013-9353-0

Keywords

Search

Navigation