当前位置: X-MOL 学术IEEE Trans. Geosci. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dehaze-AGGAN: Unpaired Remote Sensing Image Dehazing Using Enhanced Attention-Guide Generative Adversarial Networks
IEEE Transactions on Geoscience and Remote Sensing ( IF 8.2 ) Pub Date : 2022-09-07 , DOI: 10.1109/tgrs.2022.3204890
Yitong Zheng 1 , Jia Su 1 , Shun Zhang 1 , Mingliang Tao 1 , Ling Wang 1
Affiliation  

Remote sensing image dehazing is of great scientific interest and application value in both military and civil fields. In this article, we propose an enhanced attention-guide generative adversarial network (GAN) network, Dehaze-AGGAN, to solve the remote sensing images dehazing problem, which does not require paired training data. Since haze images have a great influence on remote sensing object detection, the dehazing of remote sensing images has become significantly important. Typical image dehazing methods require a hazy input image and its ground truth in a paired manner, while paired training data are usually not available in the field of remote sensing. To solve this problem, we propose the Dehaze-AGGAN network and train it by feeding unpaired clean and hazy images into the model. We present a novel total variation loss combined with the cycle consistency loss to eliminate wave noise and improve the target edge quality in the test dataset. Moreover, we present a new dehazing dataset called remote sensing dehazing dataset (RSD), which contains 7000 simulate and real hazy images including 3500 warship images and 3500 civilian ship images, and evaluate our method in the dataset. We conduct experiments on RSD. Extensive experiments demonstrate that the proposed Dehaze-AGGAN is effective and has strong robustness and adaptability in different settings.

中文翻译:

Dehaze-AGGAN:使用增强注意力引导生成对抗网络的不成对遥感图像去雾

遥感图像去雾在军事和民用领域都具有重要的科学价值和应用价值。在本文中,我们提出了一种增强的注意力引导生成对抗网络 (GAN) 网络 Dehaze-AGGAN,以解决不需要配对训练数据的遥感图像去雾问题。由于雾霾图像对遥感目标检测的影响很大,因此对遥感图像去雾就显得尤为重要。典型的图像去雾方法需要成对的模糊输入图像及其ground truth,而成对的训练数据在遥感领域通常是不可用的。为了解决这个问题,我们提出了 Dehaze-AGGAN 网络,并通过将未配对的干净和朦胧图像输入模型来对其进行训练。我们提出了一种新颖的总变化损失与循环一致性损失相结合,以消除波噪声并提高测试数据集中的目标边缘质量。此外,我们提出了一个新的去雾数据集,称为遥感去雾数据集(RSD),其中包含 7000 个模拟和真实的模糊图像,包括 3500 个军舰图像和 3500 个民用船舶图像,并在数据集中评估我们的方法。我们对 RSD 进行了实验。大量实验表明,所提出的 Dehaze-AGGAN 是有效的,并且在不同的环境中具有很强的鲁棒性和适应性。其中包含 7000 张模拟和真实的朦胧图像,包括 3500 张军舰图像和 3500 张民用船舶图像,并在数据集中评估我们的方法。我们对 RSD 进行了实验。大量实验表明,所提出的 Dehaze-AGGAN 是有效的,并且在不同的环境中具有很强的鲁棒性和适应性。其中包含 7000 张模拟和真实的朦胧图像,包括 3500 张军舰图像和 3500 张民用船舶图像,并在数据集中评估我们的方法。我们对 RSD 进行了实验。大量实验表明,所提出的 Dehaze-AGGAN 是有效的,并且在不同的环境中具有很强的鲁棒性和适应性。
更新日期:2022-09-07
down
wechat
bug