IRS: a hierarchical knowledge based system for aerial image interpretation

ABSTRACT

A knowledge based architecture for the interpretation of aerial images is presented. The Image Recognition System (IRS) utilises a multiresolution perceptual clustering methodology as a robust alternative to the more traditional edge or region based approaches. Initially, data driven feature generation and primary perceptual clustering is performed independently for two or more reduced resolution versions of the image. A Rule Based Frame System (RBFS) is then used to instantiate more complex geometrical structures from symbolic multiresolution feature representations. Final interpretation is achieved by using knowledge of contextual relations between objects in the domain.

REFERENCES

• 1: Brooks, R.A. "Model Based Computer Vision", UMI Research Press, 1984.
• 2: Mc Keown, D.M. "Rule Based Interpretation of Aerial Imagery", IEEE PAMI, Vol.7, No.5, 1985, pp 570-585.
• 3: Harwood, D., Chang, S., Davis, L.S. "Interpreting Aerial Photographs by Segmentation and Search", Prec. DARPA Image Understanding Workshop, 1987, pp507- 519.
• 4: D G Lowe, Three-dimensional object recognition from single two-dimensional images, Artificial Intelligence, v.31 n.3, p.355-395, March 1987 [doi>10.1016/0004-3702(87)90070-1]
• 5: R. Mohan , R. Nevatia, Using Perceptual Organization to Extract 3D Structures, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.11 n.11, p.1121-1139, November 1989 [doi>10.1109/34.42852]
• 6: Lillesand, T.M., Kiefer, R.W. "Remote Sensing and Image Interpretation", J. Wiley & Sons, 1979.
• 7: Tanimoto, S., Klinger, A. (Eds.) "Structured Computer Vision", Academic Press, 1980.
• 8: Virginio Cantoni , Stefano Levialdi, Pyramidal systems for computer vision, Springer-Verlag, London, 1986
• 9: J Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8 n.6, p.679-698, Nov. 1986 [doi>10.1109/TPAMI.1986.4767851]
• 10: Dana H. Ballard, Strip trees: a hierarchical representation for curves, Communications of the ACM, v.24 n.5, p.310-321, May 1981 [doi>10.1145/358645.358661]
• 11: Barber, T.J., Marshall, G., Boardman, J.T. "A Philosophy and Architecture for a Rule Based Frame System (RBFS)", Eng. Appl. of AI, Vol.1, No. 2, 1988, pp 67-85.
• 12: Kellett, J.M., Winstanley, G., Boardman, J.T. "A Methodology for Knowledge Engineering Using an Interactive Graphical Tool for Knowledge Modelling", AI in Eng., Vol. 4, No. 2, 1989, pp 92-102.
• 13: Kuczora, P.W., Cosby, S.J. "Implementation of Meronymic (Part-Whole) Inheritance For Semantic Networks", Knowledge Based Systems, Vol. 2, No. 4, 1989, pp 219-227.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Representations, data structures, and transforms
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation
          Subjects: Edge and feature detection
  I.5 PATTERN RECOGNITION

General Terms:
Design, Reliability