Advertisement

Using Deep Autoencoders to Investigate Image Matching in Visual Navigation

  • Christopher Walker
  • Paul Graham
  • Andrew PhilippidesEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10384)

Abstract

This paper discusses the use of deep auto encoder networks to find a compressed representation of an image, which can be used for visual navigation. Images reconstructed from the compressed representation are tested to see if they retain enough information to be used as a visual compass (in which an image is matched with another to recall a bearing/movement direction) as this ability is at the heart of a visual route navigation algorithm. We show that both reconstructed images and compressed representations from different layers of the auto encoder can be used in this way, suggesting that a compact image code is sufficient for visual navigation and that deep networks hold promise for finding optimal visual encodings for this task.

Keywords

Visual navigation Insect-inspired robotics Deep neural network Autoencoder 

Notes

Acknowledgements

This work was funded by the Newton Agri-Tech Program RICE PADDY project (no. STDA00732). AP and PG were also funded by EPSRC grant EP/P006094/1.

References

  1. 1.
    Graham, P., Philippides, A.: Insect-inspired vision and visually guided behavior. In: Bhushan, B., Winbigler, H.D. (eds.) Encyclopedia of Nanotechnology. Springer, Netherland (2015)Google Scholar
  2. 2.
    Wehner, R., Räber, F.: Visual spatial memory in desert ants. Cataglyphis bicolor Experientia 35, 1569–1571 (1979)CrossRefGoogle Scholar
  3. 3.
    Cartwright, B.A., Collett, T.S.: Landmark learning in bees - experiments and models. J. Comp. Physiol. 151, 521–543 (1979)CrossRefGoogle Scholar
  4. 4.
    Wehner, R.: Desert ant navigation: how miniature brains solve complex tasks. Karl von Frisch lecture. J. Comp. Physiol. A 189, 579–588 (2003)CrossRefGoogle Scholar
  5. 5.
    Wehner, R.: The architecture of the desert ant’s navigational toolkit (Hymenoptera: Formicidae). Myrmecol News 12, 85–96 (2009)MathSciNetGoogle Scholar
  6. 6.
    Smith, L., Philippides, A., Graham, P., Baddeley, B., Husbands, P.: Linked local navigation for visual route guidance. Adapt. Behav. 15, 257–271 (2007)CrossRefGoogle Scholar
  7. 7.
    Baddeley, B., Graham, P., Husbands, P., Philippides, A.: A Model of Ant Route Navigation Driven by Scene Familiarity. PLoS Comput. Biol. 8(1), e1002336 (2012)CrossRefGoogle Scholar
  8. 8.
    Ardin, P., Peng, F., Mangan, M., Lagogiannis, K., Webb, B.: Using an insect mushroom body circuit to encode route memory in complex natural environments. PLoS Comput. Biol. 12(2), e1004683 (2016)CrossRefGoogle Scholar
  9. 9.
    Möller, R., Vardy, A.: Local visual homing by matched-filter descent in image distances. Biol. Cybern. 95, 413–430 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Wystrach, A., Dewar, A., Philippides, A., Graham, P.: How do field of view and resolution affect the information content of panoramic scenes for visual navigation? A computational investigation. J. Comp. Physiol. A 202, 87–95 (2016)CrossRefGoogle Scholar
  11. 11.
    Dewar, A., Wystrach, A., Graham, P., Philippides, A.: Navigation-specific neural coding in the visual system of Drosophila. Biosystems 136, 120–127 (2015)CrossRefGoogle Scholar
  12. 12.
    Philippides, A., Baddeley, B., Cheng, K., Graham, P.: How might ants use panoramic views for route navigation? J. Exp. Biol. 214, 445–451 (2011)CrossRefGoogle Scholar
  13. 13.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  14. 14.
    Zeil, J., Hofmann, M., Chahl, J.: Catchment areas of panoramic snapshots in outdoor scenes. J. Opt. Soc. Am. A 20, 450–469 (2003)CrossRefGoogle Scholar
  15. 15.
    Stürzl, W., Zeil, J.: Depth, contrast and view-based homing in outdoor scenes. Biol. Cybern. 96, 519–531 (2007)CrossRefzbMATHGoogle Scholar
  16. 16.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Bengio, Y., Courville, A.C., Vincent, P.: Unsupervised feature learning and deep learning: A review and new perspectives. CoRR, abs/1206.5538 (2012)Google Scholar
  18. 18.
    Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)
  19. 19.
    Philippides, A., Graham, P., Baddeley, B., Husbands, P.: Using neural networks to understand the information that guides behavior: a case study in visual navigation. Artif. Neural Netw. 1260, 227–244 (2015)Google Scholar
  20. 20.
    Baddeley, B., Graham, P., Philippides, A., Husbands, P.: Holistic visual encoding of ant-like routes: navigation without waypoints. Adapt. Behav. 19, 3–15 (2011)CrossRefGoogle Scholar
  21. 21.
    Baddeley, B., Graham, P., Philippides, A., Husbands, P.: Models of visually guided routes in ants: embodiment simplifies route acquisition. In: Jeschke, S., Liu, H., Schilberg, D. (eds.) ICIRA 2011. LNCS, vol. 7102, pp. 75–84. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-25489-5_8 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Christopher Walker
    • 1
  • Paul Graham
    • 2
  • Andrew Philippides
    • 1
    Email author
  1. 1.Department of Informatics, Centre for Computational Neuroscience and RoboticsUniversity of SussexBrightonUK
  2. 2.School of Life Sciences, Centre for Computational Neuroscience and RoboticsUniversity of SussexBrightonUK

Personalised recommendations