Advertisement

Enhanced Object Segmentation for Vehicle Tracking and Dental CBCT by Neuromorphic Visual Processing with Controlled Neuron

  • Woo-Sup Han
  • Il-Song HanEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 16)

Abstract

The neuromorphic visual processing is inspired by the robust visual recognition of human brain for the robust computer vision in ordinary everyday environment, by mimicking the behavior of primary visual cortex. With the recent wide application of deep neural networks approach for pattern recognition and artificial intelligence, the proposed neuromorphic neural network of visual processing was analyzed for the ADAS and the enhanced road safety. The feasibility of proposed neuromorphic design methodology with controlled neurons is demonstrated for the object segmentation technology for the vehicle tracking at night time and the tooth segmentation of noisy dental x-ray image via maintaining the successful segmentation without complicated post-processing layers or supervised learning. The new neuron integrated with both the rectifier and the resizing enhanced the performance via the successful segmentation over 97% with the night-time road traffic, without the post-processing denoising network layer. The post enhancement or integration with further deep networks becomes more flexible from incorporating the new neuron of rectifier and resizing demonstrating the abstracting efficiency, and the simple structure has the advantages of real-time and robust neuromorphic vision implemented by the small embedded system.

Keywords

Neuromorphic visual processing Rectifier neuron Neural networks Visual cortex Machine vision Vehicle tracking CBCT 

Notes

Acknowledgment

We are particularly thankful to Mr. Ike Kim of ABC Tech for the cooperation with Vatech in our tooth segmentation research for dental 3D x-ray CBCT, specifically on the guidance and discussion about developing the medical applications. We are also grateful to Ms. Alison Lowndes of NVidia for providing GPU embedded systems in our neuromorphic vision research.

References

  1. 1.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  2. 2.
    Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurons in the cat’s striate cortex. J. Physiol. 148, 574–591 (1959)CrossRefGoogle Scholar
  3. 3.
    Hinton, G., Osrindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Scarfe, W., Farman, A.: What is Con-Beam CT and how does it work? Dental Clinincs North Am. 52, 707–730 (2008). ElsevierCrossRefGoogle Scholar
  5. 5.
    Han, W.S., Han, I.S.: Neuromorphic visual information processing for vulnerable road user detection and driver monitoring. In: Proceedings of SAI Intellisys, pp. 798–803, November 2015Google Scholar
  6. 6.
    Han, W.S., Han, I.S.: All Weather Human Detection Using Neuromorphic Visual Processing. Studies in Computational Intelligence, vol. 542, pp. 25–44 (2014)Google Scholar
  7. 7.
    Hubel, D.: A big step along the visual pathway. Nature 380, 197–198 (1996)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.ODIGA Ltd.LondonUK
  2. 2.Graduate School for Green TransportationKorea Advanced Institute of Science and TechnologyDaejonKorea

Personalised recommendations