Advertisement

Object detection in noisy images

  • V. Topkar
  • B. Kjell
  • A. Sood
Part of the NATO ASI Series book series (volume 83)

Abstract

Scale-space representation is a topic of active research in computer vision. Several researchers have studied the behavior of signals in the scale-space domain and how a signal can be reconstructed from its scale-space. However, not much work has been done on the signal detection problem, i.e. detecting the presence or absence of signal models from a given scale-space representation. In this paper we propose a model-based object detection algorithm for separating the objects from the background in the scale-space domain. There are a number of unresolved issues, some of which are discussed here. The algorithm is used to detect an infrared image of a tank in a noisy background. The performance of a multiscale approach is compared with that of a single scale approach by using a synthetic image and adding controlled amounts of noise. A synthetic image of randomly placed blobs of different sizes is used as the clean image. Two classes of noisy images arc considered. The first class is obtained by adding clutter (i.e. colored noise) and the second class by adding an equivalent amount of white noise. The multiscale and single scale algorithms are applied to delect the blobs, and performance indices such as number of detections, number of false alarms, delocalization errors etc. are computed. The results indicate that (i) the multiscale approach is better than the single scale approach and (ii) the degradation in performance is greater with clutter than with white noise.

Keywords

False Alarm Object Detection Machine Intelligence Noisy Image Single Scale 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Marr and E. Hildreth, “Theory of Edge Detection”, Proc. Royal Soc. Lond., Vol. B 207, pp. 187–217, 1980.Google Scholar
  2. 2.
    A. L. Yuille and T. A. Poggio, “Scaling theorems from zero crossings”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, pp. 15–25, 1986.CrossRefMATHGoogle Scholar
  3. 3.
    Robert Hummel and Robert Moniot, “Reconstructions from Zero Crossings in Scale Space”, IEEE Trans. Acoustics, Speech and Signal Processing, Vol. 37, No. 12, pp. 2111–2130, Dec. 1989.CrossRefGoogle Scholar
  4. 4.
    R. M. Haralick, “Digital Step Edges from Zero Crossing of Second Directional Derivatives”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 6, No. 1, Jan. 1984.Google Scholar
  5. 5.
    John Canny, “A Computational Approach to Edge Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 6, pp. 58–68, Jan. 1984.CrossRefGoogle Scholar
  6. 6.
    A. P. Witkin, “Scale Space Filtering”, Proceedings IJCAI, pp. 1019–1022, 1983.Google Scholar
  7. 7.
    W. H. H. J. Lunschcr and M. P. Bcddocs, “Optimal Edge Detector Design I: Parameter Selection and Noise Effects”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, No. 2, pp. 164–177, Mar. 1986.CrossRefGoogle Scholar
  8. 8.
    W. H. H. J. Lunscher and M. P. Beddoes, “Optimal Edge Detector Design II: Coefficient Quantization”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, No. 2, pp. 178–187, Mar. 1986.CrossRefGoogle Scholar
  9. 9.
    A. Huertas and G. Medioni, “Detection of Intensity Changes with Subpixel Accuracy Using Laplacian- Gaussian Masks”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, No. 5, pp. 651–664, Sep. 1986.CrossRefGoogle Scholar
  10. 10.
    J. J. Clarke, “Authenticating Edges Produced by Zero-Crossing Algorithm”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 11, No. 1, pp. 43–57, Jan. 1989.CrossRefGoogle Scholar
  11. 11.
    Y. Lu and R. C. Jain, “Behavior of Edges in Scale Space”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 11, No. 4, pp. 337–355, Apr. 1989.CrossRefGoogle Scholar
  12. 12.
    M. Shah, A. Sood and R. Jain, “Pulse and Staircase Edge Models”, Computer Graphics, Vision and Image Processing, Vol. 34, pp. 321–343, 1986.CrossRefGoogle Scholar
  13. 13.
    F. Bcrgholm, “Edge Focussing”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 9, No. 6, pp. 726–741, Nov. 1987.CrossRefGoogle Scholar
  14. 14.
    V. Topkar, B Kjcll and A. Sood, “Object Detection using Scale-Space”, SPIE Proc. Applications of AI, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • V. Topkar
    • 1
  • B. Kjell
    • 1
  • A. Sood
    • 1
  1. 1.George Mason UniversityFairfaxUSA

Personalised recommendations