Research Article

Automatic detection and tracking of moving image target with CNN-UM via target probability fusion of multiple features

  1. Hyongsuk Kim1,*,
  2. Támas Roska2,
  3. Leon O. Chua3,
  4. Frank Werblin4

Article first published online: 2 JUL 2003

DOI: 10.1002/cta.235

Issue

International Journal of Circuit Theory and Applications

International Journal of Circuit Theory and Applications

Volume 31, Issue 4, pages 329–346, July/August 2003

Additional Information

How to Cite

Kim, H., Roska, T., Chua, L. O. and Werblin, F. (2003), Automatic detection and tracking of moving image target with CNN-UM via target probability fusion of multiple features. Int. J. Circ. Theor. Appl., 31: 329–346. doi: 10.1002/cta.235

Author Information

  1. 1

    Division of E&I Engineering, Chonbuk National University, Chonju, 561-756, Korea

  2. 2

    C&A Research Institute of HAS, H1518 Budapest, Hungary

  3. 3

    Department of EECS, University of California, Berkeley, CA94720, U.S.A.

  4. 4

    Department of MCB, University of California, Berkeley, CA94720, U.S.A.

*Division of Electronics and Information Engineering, Chonbuk National University, Chonju, 561-756, Korea

Publication History

  1. Issue published online: 2 JUL 2003
  2. Article first published online: 2 JUL 2003
  3. Manuscript Revised: 30 AUG 2002
  4. Manuscript Received: 19 DEC 2001

Funded by

  • Office of Naval Research. Grant Number: N00014-99-1-0959 and N00014-00-0295

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (341K)

Keywords:

  • target detection;
  • confidence;
  • fusion;
  • multiple features;
  • region of influence

Abstract

A high speed target detection and tracking algorithm for a CNN-UM chip is presented in this paper. The target confidence value is computed based on the fusion of target existence probabilities of features using products of weighted sums. The target decision is done with such a confidence value and target initiation is done through the temporal accumulation of the confidence. The probability of the target existence for each feature is created in the region of influence depending on the reliability and the strength of the feature. By virtue of the analogic parallel processing structure of the CNN-UM (Roska T, Chua LO. The CNN universal machine: an analogic array computer. IEEE Trans. Circuits Systems II 1993; CAS-40: 163–173), real time tracking can be achieved with presently available technologies with the speed of several kilo-frames per second. Due to the utilization of multiple features of target, robust target detection is possible via the proposed algorithm. On-chip experiments of the proposed target-tracking algorithm have been done and properties of the proposed approach are disclosed through the various experiments. Copyright © 2003 John Wiley & Sons, Ltd.

Get PDF (341K)