Detection of moving objects in image sequences using 3D velocity filters

Sam Schauland; Joerg Velten; Anton Kummert

International Journal of Applied Mathematics and Computer Science (2008)

  • Volume: 18, Issue: 1, page 21-31
  • ISSN: 1641-876X

Abstract

top
A movement analysis of objects contained in visual scenes can be performed by means of linear multidimensional filters, which have already been analyzed in the past. While the soundness of the results was convincing, interest in those systems declined due to the limited computational power of contemporary computers. Recent advances in design and implementation of integrated circuits and hardware architectures allow realizing velocity filters if the n-D system is carefully adapted to the analyzed problem. In this paper, the fundamental principles of visual scene analysis by linear multidimensional filters are examined with respect to possible sources of degradation. The extraction of movement information and its practical use are demonstrated using a wave digital filter (WDF) implementation.

How to cite

top

Sam Schauland, Joerg Velten, and Anton Kummert. "Detection of moving objects in image sequences using 3D velocity filters." International Journal of Applied Mathematics and Computer Science 18.1 (2008): 21-31. <http://eudml.org/doc/207861>.

@article{SamSchauland2008,
abstract = {A movement analysis of objects contained in visual scenes can be performed by means of linear multidimensional filters, which have already been analyzed in the past. While the soundness of the results was convincing, interest in those systems declined due to the limited computational power of contemporary computers. Recent advances in design and implementation of integrated circuits and hardware architectures allow realizing velocity filters if the n-D system is carefully adapted to the analyzed problem. In this paper, the fundamental principles of visual scene analysis by linear multidimensional filters are examined with respect to possible sources of degradation. The extraction of movement information and its practical use are demonstrated using a wave digital filter (WDF) implementation.},
author = {Sam Schauland, Joerg Velten, Anton Kummert},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {multidimensional signal processing; velocity filters; motion filters; object detection; wave digital filters; velocity filter; visual scene signal processing},
language = {eng},
number = {1},
pages = {21-31},
title = {Detection of moving objects in image sequences using 3D velocity filters},
url = {http://eudml.org/doc/207861},
volume = {18},
year = {2008},
}

TY - JOUR
AU - Sam Schauland
AU - Joerg Velten
AU - Anton Kummert
TI - Detection of moving objects in image sequences using 3D velocity filters
JO - International Journal of Applied Mathematics and Computer Science
PY - 2008
VL - 18
IS - 1
SP - 21
EP - 31
AB - A movement analysis of objects contained in visual scenes can be performed by means of linear multidimensional filters, which have already been analyzed in the past. While the soundness of the results was convincing, interest in those systems declined due to the limited computational power of contemporary computers. Recent advances in design and implementation of integrated circuits and hardware architectures allow realizing velocity filters if the n-D system is carefully adapted to the analyzed problem. In this paper, the fundamental principles of visual scene analysis by linear multidimensional filters are examined with respect to possible sources of degradation. The extraction of movement information and its practical use are demonstrated using a wave digital filter (WDF) implementation.
LA - eng
KW - multidimensional signal processing; velocity filters; motion filters; object detection; wave digital filters; velocity filter; visual scene signal processing
UR - http://eudml.org/doc/207861
ER -

References

top
  1. Bartley N. and Bruton L. (1987). The design of highly selective adaptive three dimensional recursive cone filters, IEEE Transactions on Circuits and Systems 34(7): 775-781. 
  2. Bartley N. R. and Bruton L. T. (1986). The enhancement and tracking of moving objects in digital images using adaptive three dimensional recursive cone filters, IEEE Transactions on Circuits and Systems 33(6): 604-611. 
  3. Bolle M. (1992). Entwurfsverfahren fuer mehrdimensionale diskrete Faecherfilter, Ph.D. thesis, Ruhr-Universitaet Bochum, Germany. 
  4. Bruton L. T. and Bartley N. R. (1985). Three dimensional image processing using the concept of network resonance, IEEE Transactions on Circuits and Systems 32(7): 664-672. 
  5. Christie P.A.F, Hugher V.J. and Kennett B.L.N (1983). Velocity filtering of seismic reflection data, First Break 1(3): pp. 9-24. 
  6. Dansereau D. and Bruton L. (2007). A 4-D dual fan filter bank for depth filtering in light fields, IEEE Transactions on Signal Processing. 55(2): 542-549. 
  7. Dudgeon D. E. and Mersereau R. M. (1984). Multidimensional Digital Signal Processing. Prentice-Hall, New Jersey, USA. Zbl0643.94001
  8. Fettweis A. (1986). Wave Digital Filters: Theory and Practice, European Association for Signal Processing (EURASIP)- EURASIP Short Course. 
  9. Fettweis A. and Meerkoetter K. (1975). Suppression of parasitic oscillations in wave digital filters, IEEE Transactions on Circuits and Systems 22(12): 239-246. 
  10. Gandhi T. and Trivedi M. M. (2006). Pedestrian collision avoidance systems: A survey of computer vision based recent studies, Proceedings of the IEEE Conference on Intelligent Transportation Systems, Toronto, Canada, pp. 976-981. 
  11. Lu W.-S. and Antoniou A. (1992). Two-Dimensional Digital Filters, Boca Raton, FL, CRC Press. Zbl0852.93001
  12. Marzetta T. L. (1994). Fan filters, the 3-D Radon transform, and image sequence analysis, IEEE Transactions on Image Processing, 3(3): 253-264. 
  13. Runze G. (2005). Entwurf dreidimensionaler digitaler Geschwindigkeitsfilter zur Separation unterschiedlicher Geschwindigkeitskomponenten eines Signals, Ph.D. thesis, Universitaet Erlangen-Nuernberg, Germany. 

NotesEmbed ?

top

You must be logged in to post comments.