Abstract
The active efficient coding (AEC) framework parsimoniously explains the joint development of visual processing and eye movements, e.g., the emergence of binocular disparity selective neurons and fusional vergence, the disjunctive eye movements that align left and right eye images. Vergence can be driven by information in both the fovea and periphery, which play complementary roles. The high resolution fovea can drive precise short range movements. The lower resolution periphery supports coarser long range movements. The fovea and periphery may also contain conflicting information, e.g. due to objects at different depths. While past AEC models did integrate peripheral and foveal information, they did not explicitly take into account these characteristics. We propose here a two-level hierarchical approach that does. The bottom level generates different vergence actions from foveal and peripheral regions. The top level selects one. We demonstrate that the hierarchical approach performs better than prior approaches in realistic environments, exhibiting better alignment and less oscillation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ohzawa, I., DeAngelis, G., Freeman, R.: Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. Science 249(4972), 1037–1041 (1990)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cats striate cortex. J. Physiol. 148(3), 574–591 (1959)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cats visual cortex. J. Physiol. 160(1), 106–154 (1962)
Freeman, J., Simoncelli, E.P.: Metamers of the ventral stream. Nat. Neurosci. 14(9), 1195–1201 (2011)
Henriksson, L., Nurminen, L., Hyvarinen, A., Vanni, S., Hyvarinen, A.: Spatial frequency tuning in human retinotopic visual areas. J. Vision 8(10), 1–13 (2008)
Rawlings, S.C., Shipley, T.: Stereoscopic acuity and horizontal angular distance from fixation. J. Opt. Soc. Am. 59(8), 991–993 (1969)
Antona, B., Barrio, A., Barra, F., Gonzalez, E., Sanchez, I.: Repeatability and agreement in the measurement of horizontal fusional vergences. Ophthalmic Physiol. Opt. 28(5), 475–491 (2008)
Stevenson, S.B., Reed, P.E., Yang, J.: The effect of target size and eccentricity on reflex disparity vergence. Vision. Res. 39(4), 823–832 (1999)
Siebert, J., Wilson, D.: Foveated vergence and stereo. In: Proceedings of the 3rd International Conference on Visual Search (1992)
Westelius, C., Knutsson, H., Wiklund, J., et al.: 11. Phase-Based Disparity Estimation. Vision Process Basic Res. Comput. Vision Syst. 10 (1995)
Gibaldi, A., Chessa, M., Canessa, A., et al.: A cortical model for binocular vergence control without explicit calculation of disparity. Neurocomputing 73, 1065–1073 (2010)
Zhang, X., Tay, L.P.: Binocular vergence control using disparity energy neurons. J. Exp. Theor. Artif. Intell. 23, 201–222 (2011)
Piater, J. H., Grupen, R. A., Ramamritham, K.: Learning real-time stereo vergence control. In: Proceedings of the 1999 IEEE International Symposium on Intelligent Control/Intelligent Systems and Semiotics, pp. 272–277. IEEE (1999)
Gibaldi, A., Canessa, A., Chessa, M., et al.: How a population-based representation of binocular visual signal can intrinsically mediate autonomous learning of vergence control. Procedia Comput. Sci. 13, 212–221 (2012)
Gibaldi, A., Canessa, A., Solari, F., et al.: Autonomous learning of disparity-vergence behavior through distributed coding and population reward: basic mechanisms and real-world conditioning on a robot stereo head. Robot. Autonom. Syst. 71, 23–34 (2015)
Barlow, H.: Possible principles underlying the transformations of sensory messages. Sens. Commun. 6(2), 57–58 (1961)
Blattler, F., Hahnloser, R.H.R.: An efficient coding hypothesis links sparsity and selectivity of neural responses. PLoS ONE 6(10), e25506 (2011)
Franz, A., Triesch, J.: Emergence of disparity tuning during the development of vergence eye movements. In: IEEE 6th International Conference on Development and Learning, pp. 31–36. IEEE (2007)
Sun, W., Shi, B. E.: Joint development of disparity tuning and vergence control. In: IEEE International Conference on Development and Learning (2011)
Zhao, Y., Rothkopf, C.A., Triesch, J., Shi, B.E.: A unified model of the joint development of disparity selectivity and vergence control. In: 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics. IEEE (2012)
Lonini, L., Zhao, Y., Chandrashekhariah, P., Shi, B.E., Triesch, J.: Autonomous learning of active multi-scale binocular vision. In: 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics. IEEE (2013)
Lonini, L., Forestier, S., Teulire, C., et al.: Robust active binocular vision through intrinsically motivated learning. Front. Neurorobotics 7 (2013)
Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1), 181–211 (1999)
Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Disc. Event Dyn. Syst. 13(12), 341–379 (2003)
Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artif. Intell. Res. 13, 227–303 (2000)
Chandrapala, T.N., Shi, B.E.: Learning Slowness in a Sparse Model of Invariant Feature Detection. Neural Comput. (2015)
Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Incremental natural actor-critic algorithms. Automatica 45(11), 2471–2482 (2009)
Bruce, N.D.B., Tsotsos, J.K.: Saliency, attention, and visual search: an information theoretic approach. J. Vision 3(9), 1–24 (2009)
Martull, S., Peris, M., Fukui, K.: Realistic CG stereo image dataset with ground truth disparity maps. In: International Conference on Pattern Recognition, pp. 40–43 (2012)
Tanimoto, N., Takagi, M., Bando, T., Abe, H., Hasegawa, S., Usui, T., Zee, D.S.: Central and peripheral visual interactions in disparityinduced vergence eye movements: I. Spatial interaction. Invest. Ophthalmol. Vis. Sci. 45(4), 1132–1138 (2004)
Acknowledgements
This work was supported by the Hong Kong Research Grants Council under Grant 16244416, the German Federal Ministry of Education and Research under Grants 01GQ1414 and 01EW1603A, the European Union’s Horizon 2020 Grant 713010, and the Quandt Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Z., Triesch, J., Shi, B.E. (2018). Learning Hierarchical Integration of Foveal and Peripheral Vision for Vergence Control by Active Efficient Coding. In: Manoonpong, P., Larsen, J., Xiong, X., Hallam, J., Triesch, J. (eds) From Animals to Animats 15. SAB 2018. Lecture Notes in Computer Science(), vol 10994. Springer, Cham. https://doi.org/10.1007/978-3-319-97628-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-97628-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97627-3
Online ISBN: 978-3-319-97628-0
eBook Packages: Computer ScienceComputer Science (R0)