METRIC: a complete methodology for performances evaluation of automatic target Detection, Recognition and Tracking algorithms in infrared imagery

TL;DR

This paper introduces METRIC, a comprehensive evaluation methodology for assessing automatic target detection, recognition, and tracking algorithms in infrared imagery, emphasizing objective datasets and task-specific metrics.

Contribution

It presents a novel complete evaluation framework tailored for infrared ATD/R/T algorithms, integrating dataset development and metric definition.

Findings

Performance results from the French-MoD 2ACI program.

Validation of the proposed evaluation methodology.

Insights into algorithm effectiveness in infrared imagery.

Abstract

In this communication, we deal with the question of automatic target detection, recognition and tracking (ATD/R/T) algorithms performance assessment. We propose a complete methodology of evaluation which approaches objective image datasets development and adapted metrics definition for the different tasks (detection, recognition and tracking). We present some performance results which are currently processed in a French-MoD program called 2ACI (``Acquisition Automatique de Cibles par Imagerie``).