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

TL;DR

A complete methodology of evaluation which approaches objective image datasets development and adapted metrics definition for the different tasks (detection, recognition and tracking) is proposed.

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``).

Figures (13)

• Figure 1: Principle of ATD/R algorithm evaluation.
• Figure 2: Detection's notations.
• Figure 3: Multiple tracker (MT) and multiple objects (MO) definition.
• Figure 4: False Identified Trackers and Objects.
• Figure 5: Definition of different areas for target superimposition over a chosen background.