Restoration of Semantic-Based Super-Resolution Aerial Images

Author:

Favorskaya Margarita,Pakhirka Andrey

Abstract

Currently, technologies for remote sensing image processing are actively developing, including both satellite images and aerial images obtained from video cameras of unmanned aerial vehicles. Often such images have artifacts such as low resolution, blurred image fragments, noise, etc. One way to overcome such limitations is to use modern technologies to restore super-resolution images based on deep learning methods. The specificity of aerial images is the presentation of texture and structural elements in a higher resolution than in satellite images, which objectively contributes to better results of restoration. The article provides a classification of super-resolution methods based on the main architectures of deep neural networks, namely convolutional neural networks, visual transformers and generative adversarial networks. The article proposes a method for reconstructing super-resolution aerial images SemESRGAN taking into account semantic features by using an additional deep network for semantic segmentation during the training stage. The total loss function, including adversarial losses, pixel-level losses, and perception losses (feature similarity), is minimized. Six annotated aerial and satellite image datasets CLCD, DOTA, LEVIR-CD, UAVid, AAD, and AID were used for the experiments. The results of image restoration using the proposed SemESRGAN method were compared with the basic architectures of convolutional neural networks, visual transformers and generative adversarial networks. Comparative results of image restoration were obtained using objective metrics PSNR and SSIM, which made it possible to evaluate the quality of restoration using various deep network models.

Publisher

SPIIRAS

Reference36 articles.

1. Фаворская М.Н. Аналитическое исследование моделей глубокого обучения для создания снимков ДЗЗ сверхвысокого разрешения // Обработка пространственных данных в задачах мониторинга природных и антропогенных процессов (SDM-2023): Сб. тр. Всероссийской конф. с междунар. участ. 2023. С. 17–25.

2. Lepcha D.C., Goyal B., Dogra A., Goyal V. Image super-resolution: A comprehensive review, recent trends, challenges and applications // Information Fusion. 2023. vol. 91. pp. 230–260.

3. Goodfellow I., Pouget-Abadie J., Mirza M., Xu, B., Warde-Farley D., Ozair S., Courville A., Bengio Y. Generative adversarial nets. Advances in Neural Information Processing Systems (NIPS 2014). 2014. vol. 27. pp. 1–9.

4. Фаворская М.Н., Пахирка А.И. Улучшение разрешения снимков ДЗЗ на основе глубоких генеративно-состязательных сетей // Обработка пространственных данных в задачах мониторинга природных и антропогенных процессов (SDM-2023): Сб. тр. Всероссийской конф. с междунар. участ. 2023. С. 163–168.

5. Conde M.V., Choi U.J., Burchi M., Timofte R. Swin2SR: SwinV2 transformer for compressed image super-resolution and restoration // Computer Vision – ECCV 2022 Workshops. LNCS. Springer, Cham. 2023. vol. 13802. pp. 669–687.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. About One Way to Scan a Surface for a Home Walking Robot;Lecture Notes in Computer Science;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3