Flight Contrail Segmentation via Augmented Transfer Learning with Novel SR Loss Function in Hough Space

TL;DR

This paper presents a novel transfer learning approach with a specialized SR Loss function in Hough space for accurate flight contrail segmentation, addressing data scarcity and improving detection performance.

Contribution

It introduces a new SR Loss function in Hough space and applies transfer learning to enhance contrail segmentation with minimal labeled data.

Findings

Significant performance improvement over traditional loss functions.

Effective contrail detection with limited labeled data.

Robust segmentation results in varied remote sensing conditions.

Abstract

Air transport poses significant environmental challenges, particularly regarding the role of flight contrails in climate change due to their potential global warming impact. Traditional computer vision techniques struggle under varying remote sensing image conditions, and conventional machine learning approaches using convolutional neural networks are limited by the scarcity of hand-labeled contrail datasets. To address these issues, we employ few-shot transfer learning to introduce an innovative approach for accurate contrail segmentation with minimal labeled data. Our methodology leverages backbone segmentation models pre-trained on extensive image datasets and fine-tuned using an augmented contrail-specific dataset. We also introduce a novel loss function, termed SR Loss, which enhances contrail line detection by transforming the image space into Hough space. This transformation results in a significant performance improvement over generic image segmentation loss functions. Our approach offers a robust solution to the challenges posed by limited labeled data and significantly advances the state of contrail detection models.