A real-world limitation of visual servoing approaches is the sensitivity of visual tracking to varying ambient conditions and background clutter. The authors present a model-based vision framework to improve the robustness of edge-based feature tracking. Lines and ellipses are tracked using edge-projected integration of cues (EPIC). EPIC uses cues in regions delineated by edges that are defined by observed edgels and a priori knowledge from a wire-frame model of the object. The edgels are then used for a robust fit of the feature geometry, but at times this results in multiple feature candidates. A final validation step uses the model topology to select the most likely feature candidates. EPIC is suited for real-time operation. Experiments demonstrate operation at frame rate. Navigating a walking robot through an industrial environment shows the robustness to varying lighting conditions. Tracking objects over varying backgrounds indicates robustness to clutter.
Get full access to this article
View all access options for this article.
References
1.
Aloimonos, J., and Shulman, D. 1989. Integration of Visual Modules—An Extension of the Marr Paradigm. Boston: Academic Press .
2.
Biber, J., Vincze, M., Ayromlou, M., and Ponweiser, W. 2001. Robust real-time tracking of ellipse arcs. OAGM Austrian Pattern Recognition Workshop, Berchtesgaden .
3.
Boldt, M., Weiss, R., and Riseman, E. 1989. Token-based extraction of straight lines . IEEE Systems, Man and Cybernetics19: 1581–1594 .
4.
Christensen, H. I., ed. 1999. Computer vision systems. In Proceedings of the First International Conference of the ICVS, Lecture Notes in Computer Science. New York: Springer .
5.
Chroust, S., Vincze, M., Traxl, R., and Krautgartner, P. 2000. Evaluation of processing architecture and control law on the performance of vision-based control systems . IEEE International Workshop on Advanced Motor Control, Nagoya, Japan, March 28-31, pp. 19–24 .
6.
Corke, P. I. 1996. Visual Control of Robots: High Performance Visual Servoing. New York: Research Studies Press .
7.
Crowley, J. L., Stelmaszyk, P., Skordas, T., and Puget, P. 1992. Measurement and integration of 3-D structures by tracking edge lines . International Journal of Computer Vision8: 29–52 .
8.
Dickmanns, E. D., and Graefe, V. 1988a. Applications of dynamic monocular machine vision. Machine Vision and Applications. New York: Springer-Verlag , pp. 223–240.
9.
Dickmanns, E. D., and Graefe, V. 1988b. Dynamic monocular machine vision. Machine Vision and Applications. New York: Springer-Verlag , pp. 241–261.
10.
Eberst, C., Barth, M., Lutz, K., Mair, A., Schmidt, S., and Farber, G. 2000. Robust vision-based object recognition integrating highly redundant cues for indexing and verifi-cation . IEEE International Conference on Robotics and Automation, pp. 3757–3764 .
11.
Feiten, W., Magnussen, B., Bauer, J., Hager, G. D., and Toyama, K. 1998. Modeling and control for mobile manipulation in everyday environments . 8th International Symposium on Robotics Research.
12.
Fischler, M. A., and Bolles, R. C. 1981. Random sample consensus: A paradigm for model fitting . Communications of the ACM24: 381–395 .
13.
Fitzgibbon, A., Pilu, M., and Fisher, R. B. 1999. Direct least square fitting of ellipses . IEEE Pattern Analysis and Machine Intelligence21: 476–480 .
14.
Gamble, E. B., Geiger, D., Poggio, T., and Weinshall, D. 1989. Integration of vision modules and labeling of surface discontinuities . IEEE Transactions of the PAMI19: 1576–1581 .
15.
Gennery, D. B. 1992. Visual tracking of known three-dimensional objects . International Journal of Computer Vision7: 243–270 .
16.
Hager, G. D., and Toyama, K. 1998. The XVision-System: A portable substrate for real-time vision applications . Computer Vision and Image Understanding69(1): 23–37 .
17.
Harris, C. 1992. Tracking with rigid models. In Active Vision, ed. A. Blake and A. Yuille, 59–73. Cambridge, MA: MIT Press .
18.
Hoff, W., and Ahuja, N. 1989. Surfaces from stereo: Integrating feature matching, disparity estimation and colour detection . IEEE Transactions of the PAMI11: 121–136 .
Hutchinson, S., Hager, G. D., and Corke, P. 1996. Visual servoing: A tutorial . IEEE Transactions of the Robotics and Automation12(5): 651–670 .
21.
Inoue, K., Yoshida, H., Arai, T., and Mae, Y. 2000. Mobile manipulation of humanoids—Real time control based on manipulability and stability . IEEE International Conference on Robotics and Automation, pp. 2217–2222 .
22.
Jörg, S., Langwald, J., Stelter, J., Hirzinger, G., and Natale, C. 2000. Flexible robot-assembly using a multi-sensor approach . IEEE International Conference on Robotics and Automation, pp. 3687–3694 .
23.
Kim, D., and Nevitia, R. 1998. Recognition and localization of generic objects for indoor navigation using functionality . Image and Vision Computing16: 729–743 .
24.
Kosaka, A., and Kak, A. C. 1992. Fast vision-guided mobile robot navigation using model-based reasoning and prediction of uncertainties . CVGIP: Image Understanding56: 271–329 .
25.
Kragic, D., and Christensen, H. I. 2000. Cue integration for manipulation. In Robust Vision for Vision-Based Control of Motion, ed. M. Vincze and G. D. Hager, 1–16. New York: IEEE Press .
26.
Kraus, K. 1997. Photogrammetry. In Advanced Methods and Applications, Vol. 1, 205–215. Bonn, Germany: Dümmler Verlag .
27.
Lee, M.-S., and Medioni, G. 1999. Grouping into regions, curves, and junctions . Computer Vision and Image Understanding76(1): 54–69 .
28.
Lowe, D. G. 1992. Robust model-based motion tracking through the integration of search and estimation . International Journal of Computer Vision8: 113–122 .
29.
Nagel, H. H., Müller, T., Gengenbach, V., and Gehrke, A. 2000. Spatially-adaptive filtering in a model-based machine vision approach to robust workpiece tracking. In Robust Vision for Vision-Based Control of Motion, ed. M. Vincze and G. D. Hager, New York: IEEE Press , pp. 17–26.
30.
Ohya, A., Kosaka, A., and Kak, A. 1998. Vision-based navigation by a mobile robot with obstacle avoidance using single-camera vision and ultrasonic sensing . IEEE Transactions on Robotics and Automation14: 969–978 .
31.
Schiele, B. 2000. Towards automatic extraction and modelling of objects from image sequences . 8th International Symposium on Intelligent Robotic Systems, Reading, United Kingdom, July.
32.
Shirai, Y., Okada, R., and Yamane, T. 2000. Robust visual tracking by integrating various cues. In Robust Vision for Vision-Based Control of Motion, ed. Vincze, M., and Hager, G. D., pp. 53–66. New York: IEEE Press .
33.
Thompson, R. L., Reid, I. D., Munoz, L. A., and Murray, D. W. 2001. Providing synthetic views for teleoperation using visual pose tracking in multiple cameras . IEEE SMC A31(1): 43–54 .
34.
Tonko, M., Schäfer, K., Heimes, F., and Nagel, H. H. 1997. Towards visually servoed manipulation of car engine parts . IEEE International Conference on Robotics and Automation, pp. 3166–3171 .
35.
Toyama, K., and Hager, G. D. 1999. Incremental focus of attention for robust vision-based tracking . International Journal of Computer Vision35(1): 45–63 .
36.
Vincze, M. 2000. Real-time vision, tracking and control— Dynamics of visual servoing . IEEE International Conference on Robotics and Automation, San Francisco, CA, April 20-25.
37.
Vincze, M., Beltran, C., Gasteratos, A., Hoffgaard, S., Madsen, O., Ponweiser, W., and Zillich, M. 2001. A system to navigate a robot into a ship structure . International Conference on Vision Systems.
38.
Vincze, M., and Hager, G. D., eds. 2000. Robust Vision for Vision-Based Control of Motion. New York: IEEE Press .
39.
Vincze, M., and Weiman, C. 1997. On optimising window size for visual servoing . IEEE International Conference on Robotics and Automation, Albuquerque, NM, April 22-24, pp. 2856–2861 .
40.
Wren, C. R., Azarbayejani, A., Darrell, T., and Pentland, A. P. 1997. Pfinder: Real-time tracking of the human body . IEEE Transactions on Pattern Analysis and Machine Intelligence19: 780–785 .
41.
Wunsch, P., and Hirzinger, G. 1997. Real-time visual tracking of 3D-objects with dynamic handling of occlusion . IEEE International Conference on Robotics and Automation.
42.
Zelenka, R. 1998. Robuste Objektverfolgung in Echtzeit mittels einer hierarchischen Schichtenarchitektur. Diploma thesis, Technical University Vienna.
