G\'en\'eration de bases de donn\'ees images IR sous contraintes avec variabilit\'e thermique intrins\`eque des cibles

TL;DR

This paper introduces a method to generate large infrared image datasets by simulating target signatures with variable thermal configurations, aiding in the evaluation of automatic target recognition algorithms.

Contribution

The authors present a novel approach for simulating infrared target images with intrinsic thermal variability, enhancing dataset generation for ATR system testing.

Findings

Enables large-scale infrared dataset creation

Supports simulation of thermal variability in targets

Facilitates ATR algorithm performance evaluation

Abstract

In this communication, we propose a method which permits to simulate images of targets in infrared imagery by superimposition of vehicle signatures in background, eventually with occultants. We develop a principle which authorizes us to generate different thermal configurations of target signatures. This method enables us to easily generate huge datasets for ATR algorithms performance evaluation.