Performance evaluation of multi-sensor classification systems

A common problem in classification is to use one/more sensors to observe repeated measurements of a target's features/attributes, and in turn update the targets' posterior classification probabilities to aid in target identification. This paper addresses the following questions: 1. How do we quantify the classification performance of a sensor? 2. What happens to the posterior probabilities as the number of measurements increase? 3. Will the targets be classified correctly? While the Kalman filter allows for off-line estimation of kinematic performance (covariance matrix), a comparable approach for studying classification accuracy has not been done previously. We develop a new analytical approach for computing the long-run classification performance of a sensor and also present recursive formulas for efficient calculation of the same. We show that, under a minimal condition, a sensor will eventually classify all targets perfectly. We also develop a methodology for evaluating the classification performance of multi-sensor fusion systems involving sensors of varying quality. The contributions of this paper are 1. A simple metric to quantify a sensor's ability to discriminate between the targets being identified, and its use in comparing multiple sensors, 2. An approximate formula based on this metric to compute off-line estimates of the rate of convergence toward perfect classification, and the number of measurements required to achieve a desired level of classification accuracy, and 3. The use of this metric to evaluate classification performance of multi-sensor fusion systems.