Fused, multi-spectral automatic target recognition with XCS

ABSTRACT

We present new results from our most recent efforts in applying XCS to automatic target recognition (ATR). We place particular emphasis on ATR as a series of linked problems, which include pre-processing of multi-spectral data, detection of objects (in this case, vehicles) in that data, and identification (classification) of those objects. Multi-spectral data contains visual imagery, and additional imagery from several infrared spectral bands. The performance of XCS, with robust features, notably exceeds that of a template-based classifier on the pre-processed multi-spectral data for vehicle identification.

REFERENCES

• 1: Ravichandran, B., Gandhe, A. and Smith, R. E. (in press). Machine Learning for Robust Automatic Target Recognition. Information Fusion: The International Journal on Multi-Sensor, Multi-Source Information Fusion.
• 2: B. Ravichandran , Avinash Gandhe , R. E. Smith, XCS for robust automatic target recognition, Proceedings of the 2005 conference on Genetic and evolutionary computation, June 25-29, 2005, Washington DC, USA [doi>10.1145/1068009.1068316]
• 3: Gandhe, A., Yu, H.S., Mehra, R., Smith, R. E. (In Press). XCS for Fusing Multi-Spectral Data in Automatic Target Recognition in Bull, L., Bernado Mansilla, E., and Holmes, J. Learning Classifier Systems in Data Mining. Springer--Verlag.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

General Terms:
Algorithms

Keywords:
automatic target recognition, rule learning