Issue No. 03 - May/June (1999 vol. 14)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/5254.769882
Computer vision programs are notoriously unreliable in unconstrained environments, which is an obstacle to their widespread use. Aerial surveillance is one important area where this problem is particularly acute. The search for robustness leads in many directions. One approach is to seek architectures that lead to robust behavior. This article explores a self-adaptive approach. The authors describe a computer vision system that would automatically monitor its own performance and dynamically adapt to changing situations and requirements. Their approach is based on procedural reflection and control-system theory.
P. Robertson and J. M. Brady, "Adaptive Image Analysis for Aerial Surveillance," in IEEE Intelligent Systems, vol. 14, no. , pp. 30-36, 1999.