How to Augment for Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models?

TL;DR

This paper investigates the use of turbulence-specific image augmentation techniques to improve the robustness and accuracy of thermal-adapted deep learning object detection models under atmospheric turbulence conditions.

Contribution

It introduces three turbulence simulators for data augmentation and demonstrates their effectiveness in enhancing model performance against turbulent image distortions.

Findings

Augmentation significantly improves detection accuracy under turbulence.

Turbulence augmentation benefits even non-turbulent test sets.

Three simulators effectively generate training data for turbulence robustness.

Abstract

Atmospheric turbulence poses a significant challenge to the performance of object detection models. Turbulence causes distortions, blurring, and noise in images by bending and scattering light rays due to variations in the refractive index of air. This results in non-rigid geometric distortions and temporal fluctuations in the electromagnetic radiation received by optical systems. This paper explores the effectiveness of turbulence image augmentation techniques in improving the accuracy and robustness of thermal-adapted and deep learning-based object detection models under atmospheric turbulence. Three distinct approximation-based turbulence simulators (geometric, Zernike-based, and P2S) are employed to generate turbulent training and test datasets. The performance of three state-of-the-art deep learning-based object detection models: RTMDet-x, DINO-4scale, and YOLOv8-x, is employed on these turbulent datasets with and without turbulence augmentation during training. The results demonstrate that utilizing turbulence-specific augmentations during model training can significantly improve detection accuracy and robustness against distorted turbulent images. Turbulence augmentation enhances performance even for a non-turbulent test set.