Knowledge Bases for Visual Dynamic Scene Understanding

Ernst D. Dickmanns

Abstract

In conventional computer vision the actual 3-D state of objects is of primary interest; it is embedded in a temporal sequence analyzed in consecutive pairs. In contrast, in the 4-D approach to machine vision the primary interest is in temporal processes with objects and subjects (defined as objects with the capability of sensing and acting). All perception of 4-D processes is achieved through feedback of prediction errors according to spatiotemporal dynamical models constraining evolution over time. Early jumps to object/subject-hypotheses including capabilities of acting embed the challenge of dynamic scene understanding into a richer environment, especially when competing alternatives are pursued in parallel from beginning. Typical action sequences (maneuvers) form an essential part of the knowledge base of subjects. Expectation-based Multi-focal Saccadic (EMS-) vision has been developed in the late 1990s to demonstrate the advantages and flexibility of this approach. Based on this experience, the paper advocates knowledge elements integrating action processes of subjects as general elements for perception and control of temporal changes, dubbed ‘maneuvers’ here. − As recently discussed in philosophy, emphasizing individual subjects and temporal processes may avoid the separation into a material and a mental world; EMS-vision quite naturally leads to such a monistic view.

References

  1. Christensen H. I., Nagel H.-H. (eds.), 2006. Cognitive Vision Systems - Sampling the Spectrum of Approaches. Springer, (367 papes).
  2. Dickmanns, E.D., 2007. Dynamic Vision for Perception and Control of Motion. Springer (474 pages).
  3. Dickmanns, E.D., 2015. BarvEye: Bifocal active gaze control for autonomous driving. (this volume).
  4. “ , Graefe, V., 1988. a) Dynamic monocular machine vision. Machine Vision and Applications, Springer International, Vol. 1, pp 223-240. b) Applications of dynamic monocular machine vision. pp 241-261.
  5. Gallese V., Goldman A. 1998. Mirror Neurons and the Simulation Theory of Mind-reading. Trends in Cogn. Sci.2, pp 493-501.
  6. IV'00, 2000. Proc. Internat. Symp. on Intelligent Vehicles, Dearborn (MI), with six contributions to Expectationbased, Multi-focal, Saccadic (EMS-) vision:
  7. 1. Gregor R. et al.: EMS-Vision: A Perceptual System for Autonomous Vehicles.
  8. 2. Gregor R., Dickmanns E.D.: EMS-Vision: Mission Performance on Road Networks.
  9. 3. Hofmann U.; Rieder A., Dickmanns, E.D.: EMSVision: Applic. to 'Hybrid Adaptive Cruise Control'.
  10. 4. Luetzeler M., Dickmanns E.D.: EMS-Vision: Recognition of Intersections on Unmarked Road Networks.
  11. 5. Pellkofer M., Dickmanns E.D.: EMS-Vision: Gaze Control in Autonomous Vehicles.
  12. 6. Siedersberger K.-H., Dickmanns E.D.: EMS-Vision: Enhanced Abilities for Locomotion.
  13. Kalman, R. D. 1960. A new approach to linear filtering and prediction problems. Trans. ASME, Series D, Journal of Basic Engineering, pp 35-45.
  14. Kiverstein J.D., 2005. Naturalism and Phenomenology. Diss. Univ. Edinborough.
  15. Leontyev A. N. 2009. The Development of Mind. (Selected Works). Marxists Internet Archive. Printed by Bookmasters, Inc., Ohio.
  16. Noe Alva 2004. Action in Perception. Cambridge, MA; MIT Press.
  17. Vernon D., 2006. The Space of Cognitice Vision. In Christensen and Nagel (eds.), pp 7-24.
Download


Paper Citation


in Harvard Style

D. Dickmanns E. (2015). Knowledge Bases for Visual Dynamic Scene Understanding . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 209-215. DOI: 10.5220/0005340802090215


in Bibtex Style

@conference{visapp15,
author={Ernst D. Dickmanns},
title={Knowledge Bases for Visual Dynamic Scene Understanding},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={209-215},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005340802090215},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Knowledge Bases for Visual Dynamic Scene Understanding
SN - 978-989-758-089-5
AU - D. Dickmanns E.
PY - 2015
SP - 209
EP - 215
DO - 10.5220/0005340802090215