Abstract
We present an adaptive curvature scale space technique for extracting symbolic topographical descriptions from image data such as that of three dimensional digital terrain maps where specific image interpretation constraints play a significant role in defining the scale of analysis. In our approach we use machine learning techniques to learn efficient segmentation of image data, the Topograph, which satisfies the constraints of the application task and guarantees the quality of the solutions returned. The Topograph representation is evaluated empirically using a flight trajectory planning application where the problem involves minimising the integral under the path (sum of altitude) while satisfying the constraints of flight. It is shown how the Topograph hierarchy can be used to guarantee lower bounds on solutions for search problems of this nature by incorporating multiple resolution states and using dynamic programming techniques.
Preview
Unable to display preview. Download preview PDF.
References
Besl, P., Jain, R.: Segmentation through variable-order surface fitting. IEEE Trans. Pattern Anal. Machine Intell. 10 (1988) 167–192
Bischof, W. F., Caelli, T.: Learning structural descriptions of patterns: A new technique for conditional clustering and rule generation. Pattern Recognition. 27(5) (1994) 689–97
Caelli, T., Dreier, A.: Variations on the evidence-based object recognition theme. Pattern Recognition. 27 (1994) 185–204
Fan, T., Medioni, G., Nevatia, R.: Segmented descriptions of 3-D surfaces. IEEE Journal of Robotics and Automation. RA-3 (1987) 527–538
Fan, T., Medioni, G., Nevatia, R.: Recognizing 3-D objects using surface descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 11(11) (1989).
Gauch, J. M., Pizer, S. M.: Multiresolution analysis of ridges and valleys in greyscale images. IEEE Transactions on Pattern Analysis and Machine Intelligence. 15(6) (1993) 635–646
Jain, A. K., Dubes, R. C.: Algorithms for Clustering Data. Prentice Hall. (1988)
Nilsson, N. J.: Problem-Solving methods in artificial intelligence. McGraw-Hill Book Company. (1971)
Pearce, A., Caelli, T. Bischof, W. F.: Claret: A new relational learning algorithm for interpretation in spatial domains. In Proceedings of the Fourth International Conference on Control, Automation, Robotics and Vision (ICARV'96), Singapore. (1996) 650–654
Quinlan, J. R.: C4.5 Programs for Machine Learning. Morgan Kaufmann (1993)
Shapiro, L. G. Haralick, R. M.: Structural descriptions and inexact matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 3(5) (1981) 504–519
Suzuki, T. Mori, S.: A thinning method based on cell structure. In Proc. Int. Workshop Frontiers Handwriting Recognition, Montreal, Canada. (1990) 39–52
Wong, A. K. C., Lu, S. W., Rioux, M.: Recognition and shape synthesis of 3-D objects based on attribute hypergraphs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 11 3 (1989) 279–290
Zelinsky, A.: A mobile robot exploration algorithm. IEEE Trans. on Robotics and Automation. 8(6) (1992) 707–717
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pearce, A.R., Caelli, T., Goss, S. (1997). Adaptive curvature-based topography for learning symbolic descriptions of terrain maps. In: Sattar, A. (eds) Advanced Topics in Artificial Intelligence. AI 1997. Lecture Notes in Computer Science, vol 1342. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63797-4_81
Download citation
DOI: https://doi.org/10.1007/3-540-63797-4_81
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63797-4
Online ISBN: 978-3-540-69649-0
eBook Packages: Springer Book Archive