Advertisement

Rock Detection in a Mars-Like Environment Using a CNN

  • Federico FurlánEmail author
  • Elsa Rubio
  • Humberto Sossa
  • Víctor Ponce
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11524)

Abstract

In this paper we study the problem of rock detection in a Mars-like environment. We propose a convolutional neural network (CNN) to obtain a segmented image. The CNN is a modified version of the U-net architecture with a smaller number of parameters to improve the inference time. The performance of the methodology is proved in a dataset that contains several images of a Mars-like environment, achieving an F-score of 78.5%.

Keywords

Convolutional neural networks Rock detection Mars exploration 

Notes

Acknowledgments

We would like to express our sincere appreciation to the Instituto Politécnico Nacional and the Secretaría de Investigación y Posgrado for the economic support provided to carry out this research. This project was supported economically by SIP-IPN (numbers 20180730, 20190007, 20195835 and 20195882) and the National Council of Science and Technology of Mexico (CONACyT) (65 Frontiers of Science). F. Furlán acknowledges CONACyT for the scholarship granted towards pursuing his Ph.D. studies.

References

  1. 1.
    Castano, R., et al.: Onboard autonomous rover science. In: 2007 IEEE Aerospace Conference, pp. 1–13, March 2007.  https://doi.org/10.1109/AERO.2007.352700
  2. 2.
    Castano, R., et al.: Current results from a rover science data analysis system. In: 2005 IEEE Aerospace Conference, pp. 356–365, March 2005.  https://doi.org/10.1109/AERO.2005.1559328
  3. 3.
    Chollet, F.: Xception: Deep learning with depthwise separable convolutions. CoRR (2016)Google Scholar
  4. 4.
    Gao, Y., Spiteri, C., Pham, M.T., Al-Milli, S.: A survey on recent object detection techniques useful for monocular vision-based planetary terrain classification. Robot. Auton. Syst. 62(2), 151–167 (2014)CrossRefGoogle Scholar
  5. 5.
    Gong, X., Liu, J.: Rock detection via superpixel graph cuts. In: 19th IEEE International Conference on Image Processing (2012)Google Scholar
  6. 6.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  7. 7.
    Gor, V., Manduchi, R., Anderson, R., Mjolsness, E.: Autonomous rock detection for mars terrain. In: Space 2001 (AIAA), August 2001.  https://doi.org/10.2514/6.2001-4597
  8. 8.
    LeCun, Y.: Generalization and network design strategies. University of Toronto, Technical report (1989)Google Scholar
  9. 9.
    NASA: K10 robots: scouts for human explorers (2010). https://www.nasa.gov/centers/ames/K10/
  10. 10.
    Olson, J., Craig, D., National Aeronautics and Space Administration, Langley Research Center: NASA’s Analog Missions: Paving the Way for Space Exploration. National Aeronautics and Space Administration (2011). https://books.google.com.mx/books?id=-6hVnwEACAAJ
  11. 11.
    Rashno, A., Saraee, M., Sadri, S.: Mars image segmentation with most relevant features among wavelet and color features. In: AI & Robotics (IRANOPEN) (2015)Google Scholar
  12. 12.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  13. 13.
    Sasaki, Y.: The truth of the F-measure. School of Computer Science, University of Manchester, Technical report (2007)Google Scholar
  14. 14.
    Shang, C., Barnes, D.: Fuzzy-rough feature selection aided support vector machines for mars image classification. Comput. Vis. Image Underst. 117, 202–213 (2013)CrossRefGoogle Scholar
  15. 15.
    Furgale, P., Carle, P., Enright, J., Barfoot, T.D.: The Devon Island rover navigation dataset. Int. J. Robot. Res. 31, 707–713 (2012)CrossRefGoogle Scholar
  16. 16.
    Thompson, D., Castaño, R.: Performance comparison of rock detection algorithms for autonomous planetary geology. In: IEEE Aerospace Conference (2007)Google Scholar
  17. 17.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. I, December 2001.  https://doi.org/10.1109/CVPR.2001.990517
  18. 18.
    Xiao, X., Cui, H., Yao, M., Tian, Y.: Autonomous rock detection on mars through region contrast. Adv. Space Res. 60, 626–635 (2017)CrossRefGoogle Scholar
  19. 19.
  20. 20.
    Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Federico Furlán
    • 1
    Email author
  • Elsa Rubio
    • 1
  • Humberto Sossa
    • 1
    • 2
  • Víctor Ponce
    • 1
  1. 1.Instituto Politécnico Nacional - Centro de Investigación en ComputaciónMexico CityMexico
  2. 2.Escuela de Ingeniería y CienciasTecnológico de MonterreyZapopanMexico

Personalised recommendations