Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models

TL;DR

This paper investigates how atmospheric turbulence affects thermal object detection and introduces a data augmentation method using turbulent images to improve detector robustness.

Contribution

It proposes a novel data augmentation strategy with turbulent images to enhance thermal object detection under atmospheric turbulence conditions.

Findings

Performance improved on turbulent images

Enhanced robustness of detectors in adverse conditions

Effective augmentation strategy for thermal imagery

Abstract

Atmospheric turbulence has a degrading effect on the image quality of long-range observation systems. As a result of various elements such as temperature, wind velocity, humidity, etc., turbulence is characterized by random fluctuations in the refractive index of the atmosphere. It is a phenomenon that may occur in various imaging spectra such as the visible or the infrared bands. In this paper, we analyze the effects of atmospheric turbulence on object detection performance in thermal imagery. We use a geometric turbulence model to simulate turbulence effects on a medium-scale thermal image set, namely "FLIR ADAS v2". We apply thermal domain adaptation to state-of-the-art object detectors and propose a data augmentation strategy to increase the performance of object detectors which utilizes turbulent images in different severity levels as training data. Our results show that the proposed data augmentation strategy yields an increase in performance for both turbulent and non-turbulent thermal test images.