Reconstruction of Missing Data in Satellite Imagery Using SN-GANs

Panchal, Poojan; Raman, Vignesh Charan; Baraskar, Trupti; Sinha, Sujata; Purohit, Swaraj; Modi, Jaynam

doi:10.1007/978-981-16-4016-2_60

“…Hence, damaged areas are restored and undesired objects are discarded in images. GANs have been applied to address this issue [381][382][383][384].…”

Section: Image Inpaintingmentioning

confidence: 99%

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

Alzubaidi

¹

,

Bai

²

,

Al-Sabaawi

³

et al. 2023

View full text Add to dashboard Cite

Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.

show abstract

“…Various studies [22,[26][27][28][29][30] demonstrate the use of GANs-generated data in the training process of deep learning models to improve their performance in case of insufficient training data. GANs have been utilized in the fields of remote sensing not only to generate missing data [31,32], but also to translate data among various domains [23,[33][34][35][36][37][38]. However, in applications that require control over the data translation, conditional GANs by Mirza et al (2014) is the suitable framework to allow the generation of data conditioned by auxiliary information such as text, tags, class labels, images, etc.…”

Section: Introductionmentioning

confidence: 99%

Generation Of Dense Urban Features Using Conditional GAN

Nihal,

Kumar

2023

Preprint

0

View full text Add to dashboard Cite

This paper discusses the use of conditional Generative Adversarial Networks (GANs) to generate dense urban features in satellite images and evaluate their effectiveness in semantic segmentation tasks. High-resolution true-color satellite imagery of Mumbai, obtained from Pleiades-1A at a 0.5m resolution, is utilized for the study. The proposed Multiple Discriminator pix2pix (MD-pix2pix) model, which employs multiple discriminators and a modified training procedure, is introduced to generate realistic satellite images. The performance of the MD-pix2pix model is compared to the traditional pix2pix model using a mix dataset of real and generated satellite images. The synthesized satellite images are assessed for their effectiveness in semantic segmentation tasks using various CNN models, including VGG16-UNet, MobileNetV2-UNet, and DeepLabV3+. The study aims to overcome the limitations of existing datasets that do not include informal settlements, such as slum areas, which are common in many cities. The results indicate that the MD-pix2pix model produces more realistic satellite images with greater variability in vegetation type, slum arrangements, and built-ups than the traditional pix2pix model. The synthetically generated satellite images are also effective in semantic segmentation tasks, with better segmentation accuracy achieved using the MD-pix2pix generated images for computationally less expensive architectures such as MobileNetV2-UNet. This study highlights the potential of GANs to generate realistic satellite images for urban feature mapping and monitoring applications.

show abstract

“…Various studies (Kim & Hwang, 2022;Lv et al, 2020;Nabati, Navidan, Shahbazian, Ghorashi, & Windridge, 2020;Park, Tran, Jung, & Park, 2020;Rashid, Tanveer, & Aqeel Khan, 2019;Sedigh, Sadeghian, & Masouleh, 2019) demonstrate the use of GANs-generated data in the training process of deep learning models to improve their performance in case of insufficient training data. GANs have been utilized in the fields of remote sensing not only to generate missing data (Panchal et al, 2021;Shao, Wang, Zuo, & Meng, 2022), but also to translate data among various domains (Bermudez et al, 2019;Bermudez, Happ, Oliveira, & Feitosa, 2018;Enomoto et al, 2017Enomoto et al, , 2018Gao, Wang, & Lv, 2018;Ley, Dhondt, Valade, Haensch, & Hellwich, 2018;Singh & Komodakis, 2018). However, in applications that require control over the data translation, conditional GANs by Mirza and Osindero (2014) is the suitable framework to allow the generation of data conditioned by auxiliary information such as text, tags, class labels, images, etc.…”

Section: Introductionmentioning

confidence: 99%

Generation Of Dense Urban Features Using Conditional GAN

Nihal,

Kumar

2023

Preprint

0

View full text Add to dashboard Cite

This paper discusses the use of conditional Generative Adversarial Networks (GANs) to generate dense urban features in satellite images and evaluate their effectiveness in semantic segmentation tasks. High-resolution true-color satellite imagery of Mumbai, obtained from Pleiades-1A at a 0.5m resolution, is utilized for the study. The proposed Multiple Discriminator pix2pix (MD-pix2pix) model, which employs multiple discriminators and a modified training procedure, is introduced to generate realistic satellite images. The performance of the MD-pix2pix model is compared to the traditional pix2pix model using a mix dataset of real and generated satellite images. The synthesized satellite images are assessed for their effectiveness in semantic segmentation tasks using various CNN models, including VGG16-UNet, MobileNetV2-UNet, and DeepLabV3+. The study aims to overcome the limitations of existing datasets that do not include informal settlements, such as slum areas, which are common in many cities. The results indicate that the MD-pix2pix model produces more realistic satellite images with greater variability in vegetation type, slum arrangements, and built-ups than the traditional pix2pix model. The synthetically generated satellite images are also effective in semantic segmentation tasks, with better segmentation accuracy achieved using the MD-pix2pix generated images for computationally less expensive architectures such as MobileNetV2-UNet. This study highlights the potential of GANs to generate realistic satellite images for urban feature mapping and monitoring applications.

show abstract

Reconstruction of Missing Data in Satellite Imagery Using SN-GANs

Cited by 3 publications

References 14 publications

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

Generation Of Dense Urban Features Using Conditional GAN

Generation Of Dense Urban Features Using Conditional GAN

Contact Info

Product

Resources

About