A feature-supervised generative adversarial network for environmental monitoring during hazy days

TL;DR

This paper introduces a feature-supervised GAN model designed to improve environmental monitoring during hazy days by effectively dehazing images and enhancing detection accuracy in complex weather conditions.

Contribution

It proposes a novel feature-supervised GAN framework with multi-scale inputs and new loss functions, specifically addressing haze challenges in environmental monitoring.

Findings

Outperforms existing dehazing methods on synthetic and real datasets.

Creates a new hazy remote sensing dataset for environmental monitoring.

Enhances image quality and detection accuracy during hazy conditions.

Abstract

The adverse haze weather condition has brought considerable difficulties in vision-based environmental applications. While, until now, most of the existing environmental monitoring studies are under ordinary conditions, and the studies of complex haze weather conditions have been ignored. Thence, this paper proposes a feature-supervised learning network based on generative adversarial networks (GAN) for environmental monitoring during hazy days. Its main idea is to train the model under the supervision of feature maps from the ground truth. Four key technical contributions are made in the paper. First, pairs of hazy and clean images are used as inputs to supervise the encoding process and obtain high-quality feature maps. Second, the basic GAN formulation is modified by introducing perception loss, style loss, and feature regularization loss to generate better results. Third, multi-scale images are applied as the input to enhance the performance of discriminator. Finally, a hazy remote sensing dataset is created for testing our dehazing method and environmental detection. Extensive experimental results show that the proposed method has achieved better performance than current state-of-the-art methods on both synthetic datasets and real-world remote sensing images.