Relationships between computational system performance and recognition system performance

Abstract

The implementation of computational systems to perform intensive operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the computational power of the underlying hardware. An understanding of the inter-relationships between these factors can be an aid in making informed choices while exploring competing design possibilities. To model these relationships we have combined characterizations of ATR performance, which yield probability of classification error as a function of target model complexity, with analytical models of computational performance, which yield throughput as a function of target model complexity. Together, these constitute a parametric curve that is parameterized by target model complexity for any given recognition problem and hardware implementation. We demonstrate this approach on the problem of ATR from synthetic aperture radar imagery using a subset of the publicly released MSTAR dataset. We use this approach to characterize the achievable classification rate as a function of required throughput for various hardware configurations.

<title>Conditionally gamma- and k-distribution models for SAR ATR</title>

“…4 One approach to comparing distributions is to derive optimal recognition algorithms for each distribution and to apply these algorithms in a consistent manner to actual radar imagery. Good statistical models would be expected to yield high correct classification rates while not being computationally burdensome 10 or requiring excessive parameterization. 6 Another approach is to employ the statistical notion of goodness-of-fit testing in which test statistics of known distribution under the model assumptions are computed from actual imagery.…”