Satellite image inpainting with deep generative adversarial neural networks

Zaytar, Mohamed Akram; Amrani, Chaker El

doi:10.11591/ijai.v10.i1.pp121-130

Cited by 7 publications

(7 citation statements)

References 32 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the scope of this work, the main comparison made in the context of inpainting is between the conventional stacked variant used in [ 16 ] and the proposed MCPN variants (Emergent and Direct). While other recent works on satellite image inpainting have been published, such as [ 24 , 25 ], they do not address the same problem treated in this work, as they do not operate on multi-modal guidance data and do not solve the problem via internal learning. Furthermore, at the time of writing, the source code and weights have not been provided for these works.…”

Section: Discussionmentioning

confidence: 99%

Multi-Modal Convolutional Parameterisation Network for Guided Image Inverse Problems

Czerkawski,

Upadhyay,

Davison

et al. 2024

J. Imaging

View full text Add to dashboard Cite

There are several image inverse tasks, such as inpainting or super-resolution, which can be solved using deep internal learning, a paradigm that involves employing deep neural networks to find a solution by learning from the sample itself rather than a dataset. For example, Deep Image Prior is a technique based on fitting a convolutional neural network to output the known parts of the image (such as non-inpainted regions or a low-resolution version of the image). However, this approach is not well adjusted for samples composed of multiple modalities. In some domains, such as satellite image processing, accommodating multi-modal representations could be beneficial or even essential. In this work, Multi-Modal Convolutional Parameterisation Network (MCPN) is proposed, where a convolutional neural network approximates shared information between multiple modes by combining a core shared network with modality-specific head networks. The results demonstrate that these approaches can significantly outperform the single-mode adoption of a convolutional parameterisation network on guided image inverse problems of inpainting and super-resolution.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Modal Convolutional Parameterisation Network for Guided Image Inverse Problems

Czerkawski,

Upadhyay,

Davison

et al. 2024

J. Imaging

View full text Add to dashboard Cite

show abstract

“…The SRTM-DEM was used in this study because it has a good, precise resolution of 1 arcsec (30×30 m). The weakness of Landsat is the presence of clouds [32]. The water flow was obtained through the analysis of rainfall data.…”

Section: Materials and Methods 21 Research Methodsmentioning

confidence: 99%

Geological aspect analysis for micro hydro power plant site selection based on remote sensing data

Kumoro

Susilowati

Irasari

et al. 2022

IJECE

View full text Add to dashboard Cite

<span>Geological characters analysis is essential for micro hydropower plant (MHP) development planning. This paper presents an analysis of the geological aspect to determine the layout of MHP components based on remote sensing data as part of a solution to addressing power shortages in Sungai Are District, South Ogan Komering Ulu Regency, South Sumatra Province. Remote sensing and topographic map were extracted to identify the potential site. The topographic map and geological analysis were used to calculate the potential of electrical energy and the geological hazard risk, particularly floods and landslides. The results of the study identified four potential sites. Site 1 (Luas River, Ulu Danau Village) and site 3 (Putih River, Gintung Village) are suitable for MHP with a low cost of construction. Site 2 (Pecah Pinggan Village) and site 4 (Simpang Luas Village) are prone to flooding and landslides that makes it suitable for MHP but with a high cost of construction. Based on the geological aspect analysis, it is possible to optimize the hydropower capacity, by adding the volume of water flow from several nearby tributaries channeled into the hydropower flow system through civil construction engineering or by making a cascade design on the tailrace water flow.</span>

show abstract

“…This score is calculated from the precision and recall harmonic mean. The calculation of F-score is defined as (25),…”

Section: Impact Of F-scorementioning

confidence: 99%

“…Several rule-based anomaly detection techniques were implemented for precise detection of anomalies in the network, but these approaches classified only known attacks [18], [19]. The evaluation of several machine learning and deep learning algorithms against conventional intrusion detection algorithms was carried out to conclude the efficacy of those algorithms but those algorithms were effective only for particular types of attacks [20]- [25]. The execution of hybrid-based IDS was found to be more efficient in detecting the anomalies in the network [26].…”

Section: Introductionmentioning

confidence: 99%

Three level intrusion detection system based on conditional generative adversarial network

Abdulameer¹,

Musa²,

Salim

2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Security threat protection is important in the internet of things (IoT) applications since both the connected device and the captured data can be hacked or hijacked or both at the same time. To tackle the above-mentioned problem, we proposed three-level intrusion detection system conditional generative adversarial network (3LIDS-CGAN) model which includes four phases such as first-level intrusion detection system (IDS), second-level IDS, third-level IDS, and attack type classification. In first-level IDS, features of the incoming packets are extracted by the firewall. Based on the extracted features the packets are classified into three classes such as normal, malicious, and suspicious using support vector machine and golden eagle optimization. Suspicious packets are forwarded to the second-level IDS which classified the suspicious packets as normal or malicious. Here, signature-based intrusions are detected using attack history information, and anomaly-based intrusions are detected using event-based semantic mapping. In third-level IDS, adversary packets are detected using CGAN which automatically learns the adversarial environment and detects adversary packets accurately. Finally, proximal policy optimization is proposed to detect the attack type. Experiments are conducted using the NS-3.26 network simulator and performance is evaluated by various performance metrics which results that the proposed 3LIDS-CGAN model outperforming other existing works.</span>

show abstract

Satellite image inpainting with deep generative adversarial neural networks

Cited by 7 publications

References 32 publications

Multi-Modal Convolutional Parameterisation Network for Guided Image Inverse Problems

Multi-Modal Convolutional Parameterisation Network for Guided Image Inverse Problems

Geological aspect analysis for micro hydro power plant site selection based on remote sensing data

Three level intrusion detection system based on conditional generative adversarial network

Contact Info

Product

Resources

About