Dynamic Robot Vision
In computer vision efficient methods for detection and interpretation of motion of objects have been developed. As technology advances, the ambition to include this ability in robot vision systems appears more and more realistic. However, to become of practical use, real time performance (in some sense) is required, and the current possibilities for this are still limited.
Many different approaches to motion analysis have been proposed in the literature. Motion information may be derived from image analysis systems at different levels of the general scheme of image processing and interpretation. However, to achieve a result in terms of motion descriptions, most of these methods depend extensively on image preprocessing (and interpretation) or on integration into an image postprocessing (and interpretation) system.
A number of methods are reviewed and evaluated with regard to dependency on supplementary processing and with regard to current potential for real time application. Also we discuss their weaknesses due to problems of ambiguity and noise. However, one can take into account that real time operation also means continuous operation and thereby that a temporal context is provided. This allows concentration on changes most of which are predictable, and savings in computing as well as improved robustness to noise and ambiguities can be achieved.
In conclusion we find that high level token matching currently is one of the most promising approaches, and an experimental implementation is used to demonstrate a possible approach to motion analysis in real time.
This research has in part been sponsored by the Danish Technical Research Council, FTU grant 184.108.40.206.06
KeywordsMotion Analysis Real Time Operation Motion Detection Image Flow Temporal Context
Unable to display preview. Download preview PDF.
- K.J. Aaström, B. Wittenmark: Computer controlled systems, Prentice-Hall, Englewood Cliffs, NJ, 1984Google Scholar
- J. Aggarwal: On the computation of motion from a sequence on monocular or stereo images, — an overview. In: A.K.C. Wong, A. Pugh (eds.): Machine intelligence and knowledge engineering for robotics applications NATO ASI Series F, Vol. 33, Springer-Verlag, Berlin-Heidelberg-New York, 1987Google Scholar
- R.L. Andersson: Real time gray scale video processing using a moment generating chip, IEEE Robotics and Automation, Vol. RA-1, No. 2, June 1985Google Scholar
- J. Arnspang: Determining optic flow Ph.D. thesis, Dept. of Computer Science, Copenhagen University, Denmark, January 1988Google Scholar
- H.I. Christensen: Monitoring moving objects in real-time M.Sc. Thesis, Inst, of Electronic Systems, Aalborg University, June 1987Google Scholar
- H.I. Christensen, E. Granum: On token matching in real-time motion analysis. In: Proc. BPRA Pattern Recognition. 4th Int. Conf.. Cambridge. Mar. 1988. J. Kittler (ed.), Lecture Notes in Computer Science, Vol. 301, Springer-Verlag, Berlin-Heidelberg-New York, pp. 448–457, 1988aGoogle Scholar
- J. Ciccotelli, M. Dufaut, R. Husson: Control of tracking systems by image correlation. Robotics, Vol. 5, pp. 201–206, 1987Google Scholar
- J.L. Crowley, P. Stelmaszyk, C. Discours: Measuring image flow by tracking edge-lines, 2nd ICCV, Florida, Dec. 1988Google Scholar
- O.D. Faugeras, F. Lustman, G. Toscani: Motion and structure from motion from point and line matches, Proc. 1st ICCV, London, pp. 35–54, June 1987Google Scholar
- E. Granum, K.H. Munk: Monitoring moving objects in real-time, BAG-memo 8607, Inst, of Electronic Systems, Aalborg University, March 1986Google Scholar
- D.J. Heeger: Optical flow from spatio-temporal filters, Proc. 1st Int. Conf. on Computer Vision, IEEE, pp. 181–190, London, June 1987Google Scholar
- B.K.P. Horn: Robot vision, McGraw Hill, New York, 1986Google Scholar
- T.S. Huang (ed.), Image sequence processing and dynamic scene analysis, Springer Verlag, Berlin-Heidelberg-New York, 1983Google Scholar
- B. Jähne: Image sequence analysis of complex physical objects: nonlinear small scale water surface waves, Proc. 1st ICCV, London, pp. 191–200, June 1987Google Scholar
- M. Jenkin: Tracking three dimensional moving light displays. Proc. Workshop Motion Representation Contr., Toronto, Ont., Canada, pp. 66–70, 1983Google Scholar
- H.H. Nagel: Image sequence analysis: what can we learn from applications?: In: T.S. Huang (ed.): Image Sequence Analysis Springer Verlag, New York, pp. 19–228, 1981.Google Scholar
- H.H. Nagel: Overview on image sequence analysis. In: T.S. Huang (ed.): Image Sequence Processing & Dynamic Scene Analysis Berlin-Heidelberg-New York, NATO ASI serie F. Vol. 2, pp. 2–39, 1983Google Scholar
- J. O’Rourke, N.L. Badler: Model-based Iimage analysis of human motion using constraint propagation, IEEE Trans, on PAMI, Vol. PAMI-2, No. 6, Nov. 1980Google Scholar
- R.F. Rashid: Towards a system for the interpretation of moving light displays, IEEE Trans, on PAMI, Vol. PAMI-2, No. 6, Nov. 1980Google Scholar
- J.W. Roach, J.K. Aggarwal: Determining the movement of objects from a sequence of images, IEEE Trans, on PAMI, Vol. 2, No. 6, November, 1980Google Scholar
- J.K. Tsotsos, J. Mylopoulos, H. Dominic Cowey, S.W. Zucker: A framework for visual motion understanding, IEEE Trans, on PAMI, Vol. PAMI-2, No. 6, Nov. 1980Google Scholar
- S. Ullman: The interpretation of visual motion, MIT Press, Massachusetts, 1979Google Scholar
- A. Verri, T. Poggio: Against quantitative optical flow, Proc. 1st ICCV, London, pp. 171–180, June 1987Google Scholar
- A.M. Waxman, B. Kamgar-Parsi, M. Subbarao: Closed-form solutions to image flow equations, Proc. 1st ICCV, London, pp. 25–34, June 1987Google Scholar
- A.M. Waxman, J.J. LeMoigne, L.S. Davis, B. Srinivasan, T.R. Kushner, E. Liang, T. Siddalingaiah: A visual navigation system for autonomous land vehicles, IEEE Journal of Robotics and Automation, Vo. RA-3, No. 2, april 1987Google Scholar
- J. Wiklund, G. Granlund: Image sequence analysis for object tracking. Proc. 5th Scand. Conf. on Image Analysis, Stockholm, June 1987Google Scholar