Abstract
Machine vision will be a key technique in future robotics. Though we are still far from the construction of robots with human capabilities, machine vision already plays an increasingly important role in many robot applications. In this contribution, we will outline a man machine interaction scenario as an example what can be achieved by now using adaptive methods in machine vision. We will discuss the problems of current vision systems and outline possible future developments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
E. Braun, G. Heidemann, H. Ritter, and G. Sagerer. A multi-directional multiple path recognition scheme for complex objects. Pattern Recognition Letters, special issue on Pattern Recognition in Practice VI, Vlieland, June 99, 1999.
V. Bruce and M. Morgan. Violations of symmetry and repetition in visual patterns. Psychological Review, 61: 183–193, 1954.
H.I. Christensen. The AUC robot camera head. In SPIE, volume 1708, pages 26–33, 1992.
H.I. Christensen. Hardware for the the AUC camerahead (2nd generation). Persönliche Kommunikation, 1994.
M. Fislage, R. Rae, and H. Ritter. Using visual attention to recognize human pointing gestures in assembly tasks. In 7th IEEE Int’l Conf on Computer Vision, 1999.
D. Harwood, M. Subbarao, H. Hakalahti, and L. Davis. A new class of edge-preserving smoothing filters. Pattern Recognition Letters, 6: 155–162, 1986.
G. Heidemann and H. Ritter. Efficient Vector Quantization using the WTA-rule with Activity Equalization. Neural Processing Letters, 13 (1): 17–30, 2001.
G. Heidemann and H. Ritter. Visual checking of grasping positions of a three-fingered robot hand. In H. Bischof G. Dorffner and K. Hornik, editors, Proc. ICANN 2001, pages 891–898. Springer-Verlag, 2001.
G. Heidemann. Ein flexibel einsetzbares Objekterkennungssystem auf der Basis neuronaler Netze. PhD thesis, Univ. Bielefeld, Technische Fakultät, 1998. Infix, DISKI 190.
J. Jockusch. Exploration based on Neural Networks with Applications in Manipulator Control. PhD thesis, Univ. Bielefeld, Technische Fakultät, 2000.
T. Kalinke and W. von Seelen. Entropie als Maß des lokalen Informationsgehalts in Bildern zur Realisierung einer Aufmerksamkeitssteuerung. In B. Jähne, P. Geißler, H. Außecker, and F. Hering, editors, Mustererkennung 1996, pages 627–634. Springer Verlag Heidelberg, 1996.
T. Kohonen. Self-organization and associative memory. In Springer Series in Information Sciences 8. Springer-Verlag Heidelberg, 1984.
J. Lloyd and M. Parker. Real time control under unix for rccl. In Robotics and Manufacturing ISRAM 90,volume 3, pages 237–242, 1990.
P.J. Locher and C.F. Nodine. Symmetry catches the eye. In A. Levy-Schoen and J.K. O’Reagan, editors, Eye Movements: From Physiology to Cognition, pages 353–361. Elsevier Science Publishers B. V. ( North Holland ), 1987.
G. Menkhaus. Präattentive fokussierungspunktgenerierung zur objekterkennung mit künstlichen neuronalen netzen. Master’s thesis, Univ. Bielefeld, Technische Fakultät, Jan 1997.
R. Menzel, K. Woelfl, and F. Pfeiffer. The development of a hydraulic hand. In 2nd Conf. on Mechatronics and Robotics, pages 225–238, 1993.
B. Moghaddam and A. Pentland. Probabilistic visual learning for object representation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(7):696–710,1997.
H. Murase and S.K. Nayar. Visual learning and recognition of 3-d objects from appearance. Int’l J. Computer Vision,14:5–24, 1995.
T.W. Nattkemper. Untersuchung und Erweiterung eines Ansatzes zur modellfreien Aufmerksamkeitssteuerung durch lokale Symmetrien in einem Computer Vision System. Master’s thesis, Univ. Bielefeld, Technische Fakultät, Jan 1997.
S.A. Nene, S.K. Nayar, and H. Murase. Columbia Object Image Library (COIL-20). Technical Report CUCUS-006-96, Dept. Computer Science, Columbia Univ. New York, N.Y. 10027, 1996.
T. Poggio and S. Edelman. A network that learns to recognize three dimensional objects. Nature, pages 263–266, 1990.
L. Priese and V. Rehrmann. A fast hybrid color segmentation method. In S. Pöppel and H. Handels, editors, Proc. 15th DAGM Symposium Mustererkennung 1993, pages 297–304, Lübeck, Germany, 1993. Springer Verlag, Heidelberg.
R. Rae. Gestikbasierte Mensch-Maschine-Kommunikation auf der Grundlage visueller Aufmerksamkeit und Adaptivität. PhD thesis, Univ. Bielefeld, Technische Fakultät, 2000.
V. Rehrmann. Stabile, echtzeitfähige Farbbildauswertung. PhD thesis, Fölbach, 1994.
D. Reisfeld, H. Wolfson, and Y. Yeshurun. Context-free attentional operators: The generalized symmetry transform. Int’l J. of Computer Vision, 14: 119–130, 1995.
H.J. Ritter, T.M. Martinetz, and K.J. Schulten. Neuronale Netze. Addison-Wesley, München, 1992.
T.D. Sanger. Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks, 2: 459–473, 1989.
J. Steil, G. Heidemann, J. Jockusch, R. Rae, N. Jungclaus, and H. Ritter. Guiding attention for grasping tasks by gestural instruction: The gravis-robot architecture. In Proc. IROS 2001, 2001.
M.E. Tipping and C.M. Bishop. Mixtures of probabilistic principal component analyzers. Neural Computation, 11(2):443–482,1999.
M. Turk and A. Pentland. Eigenfaces for recognition. J. Cognitive Neuroscience, 3: 71–86, 1991.
T. Westman, D. Harwood, T. Laitinen, and M. Pietikäinen Colour segmentation by hierarchical connected components analysis with image enhancement by symmetric neighborhood filters. In Proc. 10th Int’l Conf. on Pattern Recognition, pages 796–802, Atlantic City, NJ, 1990.
H. Zabrodsky, S. Peleg, and D. Avnir. Symmetry as a continous feature. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17 (12): 1154–1166, 1995.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Heidemann, G., Ritter, H. (2003). Learning by Experience. In: Kühn, R., Menzel, R., Menzel, W., Ratsch, U., Richter, M.M., Stamatescu, IO. (eds) Adaptivity and Learning. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-05594-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-662-05594-6_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-05510-2
Online ISBN: 978-3-662-05594-6
eBook Packages: Springer Book Archive