Abstract
This paper presents a knowledge-based system to interpret laser radar (ladar) images. The objective of this research is to detect and recognize man-made objects in outdoor scenes. Our system applies themultisensor fusion approach to multiple ladar modalities to improve both segmentation and interpretation. The segmentation modules are written in C. The knowledge-based interpretation system is constructed usingKEE and Lisp. Low-level attributes of image segments (regions) are computed by the segmentation modules and then converted to theKEE format. The interpretation system applies forward chaining in a bottom-up fashion to derive object-level interpretation from input generated by low-level processing and segmentation modules. The interpretation modules detect man-made objects from the background using low-level attributes. Segments are grouped into objects, which are then classified into predefined categories (vehicles, ground, etc.). The efficiency of the interpretation system is enhanced by transferring nonsymbolic processing tasks to a concurrent service manager (program). Experimental results using ladar data are presented.
Similar content being viewed by others
References
Bachman CG (1979) Laser radar systems and techniques. Artech House, Dedham MA
Belknap R, Riseman EM, Hanson AR (1985) The information fusion problem and rule-based hypotheses applied to complex aggregations of image events. In: The Proceedings of DARPA Image Understanding Workshop. Miami Beach, FL, December 9–10, pp 279–292
Bhanu B, Symosek P (1987) In: Interpretation of terrain using hierarchical symbolic groupings for multi-spectral images. In: The Proceedings of DARPA Image Understanding Workshop. Los Angeles, CA, February, pp 466–474
Brown WM, Swonger CW (1989) A prospectus for automatic target recognition. IEEE Transactions on Aerospace and Electronics Systems AES-25(3):401–410, May
Buchanan BG, Shortliffe EH (1984) Rule-Based Expert Systems. Addison-Wesley, Reading, MA
Chu C, Nandhakumar N, Aggarwal JK (1988) Information integration and scene segmentation for laser radar images. In: Proceedings of the Pattern Recognition for Advanced Missile Systems Conference. Huntsville AL, November 14–15, pp 93–105
Chu C, Nandhakumar N, Aggarwal JK (1990) Image segmentation using laser radar data. Pattern Recognition 23:569–581
Clancey WJ (1985) Heuristic classification. Artificial Intelligence 27:289–350
Daily MJ, Harris JG, Reiser K (1987) Detecting obstacles in range imagery. In: The Proceedings of DARPA Image Understanding Workshop. Los Angeles, CA, February, pp 87–97
Daily MJ, Harris JG, Reiser K (1988) An operational perception system for cross-country navigation. In: The Proceedings of DARPA Image Understanding Workshop. Cambridge, MA, pp 568–575
Darwish AM, Jain AK (1988) A rule-based approach to visual pattern inspection. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-10(1):56–68, January
Davis R, King JJ (1984) The origin of rule-based systems in AI. In: Buchanan and Shortliffe (eds.) Rule-Based Expert Systems. Addison-Wesley, Reading, MA pp 20–52
Draper BA, Brolio J, Collins RT, Hanson AR, Riseman EM (1988) Image interpretation by distributed cooperative process. In: The Proceedings of Computer Vision and Pattern Recognition. Ann Arbor, MI, June 5–9, pp 129–135
Draper BA, Collins RT, Brolio J, Griffith J, Hanson AR, Riseman EM (1987) Tools and experiments in the knowledge-directed interpretation of road scenes. In: The Proceedings of DARPA Image Understanding Workshop. Los Angeles, CA, February, pp 179–193
Draper BA, Collins RT, Brolio J, Hanson AR, Riseman EM (1989) The schema system. International Journal of Computer Vision 2:209–250
Dudgeon DE, Verly JG, Delanoy RL (1988) An experimental system for recognizing targets in laser radar imagery. In: Proceedings of the Pattern Recognition for Advanced Missile Systems Conference. Huntsville, AL, November 14–15, pp 107–116
Dudgeon DE, Verly JG, Delanoy RL (1989) An experimental target recognition system for laser radar imagery. In: The Proceedings of DARPA Image Understanding Workshop. Palo Alto, CA, May, pp 479–506
Fan TJ, Medioni G, Nevatia R (1988) 3D object recognition using surface description. In: Proceedings of DARPA Image Understanding Workshop. April, pp 383–397
Fowler CA (1989) Three R's of radar: Recollections, remonstrances, and ruminations. IEEE Aerospace and Electronics Systems Magazine August, pp 18–25
Garvey TD (1987) Survey of AI approaches to the integration of information. In: Proceedings of SPIE. Vol. 782, May, pp 68–82
Gupta A, Forgy CL, Kalp D, Newell A, Tambe M (1988) Parallel OPS5 on the encore multimax. In: The Proceedings of International Conference of Parallel Processing, pp 271–280
Harwood D, Chang S, Davis LS (1987) Interpreting aerial photographs by segmentation and search. In: The Proceedings of DARPA Image Understanding Workshop. Los Angeles, CA, February, pp 507–520
Herbert M, Kanade T (1988) 3-D vision for outdoor navigation by an autonomous vehicle. In: The Proceedings of DARPA Image Understanding Workshop. Cambridge, MA, pp 593–601
Herbert M, Kanade T (1988) 3-D vision for outdoor navigation by an autonomous vehicle. In: The Proceedings of DARPA Image Understanding Workshop. Cambridge, MA, pp 593–601
Hwang VS, Davis LS, Matsuyama T (1986) Hypothesis integration in image understanding systems. Computer Vision, Graphics, and Image Processing 36:321–371
IntelliCorp (1986)KEE Software Development System User's Manual, IntelliCorp
Jain AK, Hoffman R (1988) Evidence-based recognition of 3-D objects. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-10(6):783–802, November
Kohler RR (1984) Integrating non-semantic knowledge into image segmentation process. COINS Technical Report 84-04, University of Massachusetts
Lawton DT, Levitt TS, Gelband P (1988) Knowledge based visions for terrestrial robots. In: The Proceedings of DARPA Image Understanding Workshop. Cambridge, MA, pp 103–110
Letaick D, Renhorn I, Steinvall O, Shapiro JH (1989) Noise sources in laser radar systems. Applied Optics 28(13):2657–2665, July
Levine MD, Nazif AM (1985) Low level image segmentation: An expert system. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-6(5):555–577, September
McKeown Jr., DM, Denlinger JL (1988) Cooperative methods for road tracking in aerial imagery. In: The Proceedings of DARPA Image Understanding Workshop. Cambridge, MA, pp 327–341
McKeown Jr., DM, Harvey WA (1987) Automating knowledge acquisition for aerial image interpretation. In: The Proceedings of DARPA Image Understanding Workshop, Los Angeles, CA, February, pp 205–226
McKeown Jr. DM, Harvey WA, McDermott J (1985) Rule-based interpretation of aerial imagery. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-7(5):570–585, September
Mulder JA, Mackworth AK, Havens WS (1988) Knowledge structuring and constraint satisfaction: The Mapsee approach. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-10(9):866–879, November
Ohta Y (1985) Knowledge-based interpretation of outdoor natural color scenes. Pitman Publishing, Marshfield, MA
Olin KE, Vilnrotter FM, Daily MJ, Reiser K (1987) Developments in knowledge-based vision for obstacle detection and avoidance. In: The Proceedings of DARPA Image Understanding Workshop. Los Angeles, CA, February, pp 78–86
Rich E (1983) Artificial intelligence. McGraw-Hill, New York
Shafer G (1976) A mathematical theory of evidence. Princeton, NJ Princeton University Press
Shapiro JH, Capron BA, Harney RC (1981) Imaging and target detection with a heterodyne-reception optical radar. Applied Optics 20(19):3292–3313, October
Shapiro LG (1985) The role of AI in computer vision. The Second Conference on Artificial Intelligence Applications. Miami Beach, FL, December 11–13, 76–81
Skolnik MI (1980) Introduction to radar systems. McGraw-Hill, New York
Tong CW, Rogers SK, Mills JP, Kabrisky MK (1987) Multisensor data fusion of laser radar and forward looking infrared (FLIR) for target segmentation and enhancement. In: Proceedings of SPIE. Vol. 782, May, pp 10–19
Wang JY, Pruitt PA (1984) Laboratory target reflectance measurements for coherent laser radar applications. Applied Optics 23(15):2559–2564, August
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chu, CC., Aggarwal, J.K. The interpretation of laser radar images by a knowledge-based system. Machine Vis. Apps. 4, 145–163 (1991). https://doi.org/10.1007/BF01230198
Issue Date:
DOI: https://doi.org/10.1007/BF01230198