arXiv subjects

Alessandro Sebastianelli

Publications and source records attributed to Alessandro Sebastianelli.

28 records · Page 2Linked to original sources

arXiv2022

A speckle filter for Sentinel-1 SAR Ground Range Detected data based on Residual Convolutional Neural Networks

In recent years, machine learning (ML) algorithms have become widespread in all the fields of remote sensing (RS) and earth observation (EO). This has allowed the rapid development of new procedures to solve problems affecting these sectors. In this context, this work aims at presenting a novel method for filtering speckle noise from Sentinel-1 ground range detected (GRD) data by applying deep learning (DL) algorithms, based on convolutional neural networks (CNNs). The paper provides an easy yet very effective approach to extract the large amount of training data needed for DL approaches in this challenging case. The experimental results on simulated speckled images and an actual SAR dataset show a clear improvement with respect to the state of the art in terms of peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), equivalent number of looks (ENL), proving the effectiveness of the proposed architecture.

cs.AI↗

arXiv2022

Spatio-Temporal SAR-Optical Data Fusion for Cloud Removal via a Deep Hierarchical Model

Cloud removal is a relevant topic in Remote Sensing as it fosters the usability of high-resolution optical images for Earth monitoring and study. Related techniques have been analyzed for years with a progressively clearer view of the appropriate methods to adopt, from multi-spectral to inpainting methods. Recent applications of deep generative models and sequence-to-sequence-based models have proved their capability to advance the field significantly. Nevertheless, there are still some gaps, mostly related to the amount of cloud coverage, the density and thickness of clouds, and the occurred temporal landscape changes. In this work, we fill some of these gaps by introducing a novel multi-modal method that uses different sources of information, both spatial and temporal, to restore the whole optical scene of interest. The proposed method introduces an innovative deep model, using the outcomes of both temporal-sequence blending and direct translation from Synthetic Aperture Radar (SAR) to optical images to obtain a pixel-wise restoration of the whole scene. The advantage of our approach is demonstrated across a variety of atmospheric conditions tested on a dataset we have generated and made available. Quantitative and qualitative results prove that the proposed method obtains cloud-free images, preserving scene details without resorting to a huge portion of a clean image and coping with landscape changes.

cs.CV↗

arXiv2021

On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification

This article aims to investigate how circuit-based hybrid Quantum Convolutional Neural Networks (QCNNs) can be successfully employed as image classifiers in the context of remote sensing. The hybrid QCNNs enrich the classical architecture of CNNs by introducing a quantum layer within a standard neural network. The novel QCNN proposed in this work is applied to the Land Use and Land Cover (LULC) classification, chosen as an Earth Observation (EO) use case, and tested on the EuroSAT dataset used as reference benchmark. The results of the multiclass classification prove the effectiveness of the presented approach, by demonstrating that the QCNN performances are higher than the classical counterparts. Moreover, investigation of various quantum circuits shows that the ones exploiting quantum entanglement achieve the best classification scores. This study underlines the potentialities of applying quantum computing to an EO case study and provides the theoretical and experimental background for futures investigations.

eess.IV↗

arXiv2021

On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery

In recent years, the growth of Machine Learning (ML) algorithms has raised the number of studies including their applicability in a variety of different scenarios. Among all, one of the hardest ones is the aerospace, due to its peculiar physical requirements. In this context, a feasibility study and a first prototype for an Artificial Intelligence (AI) model to be deployed on board satellites are presented in this work. As a case study, the detection of volcanic eruptions has been investigated as a method to swiftly produce alerts and allow immediate interventions. Two Convolutional Neural Networks (CNNs) have been proposed and designed, showing how to efficiently implement them for identifying the eruptions and at the same time adapting their complexity in order to fit on board requirements.

cs.CV↗

arXiv2021

Advantages and Bottlenecks of Quantum Machine Learning for Remote Sensing

This concept paper aims to provide a brief outline of quantum computers, explore existing methods of quantum image classification techniques, so focusing on remote sensing applications, and discuss the bottlenecks of performing these algorithms on currently available open source platforms. Initial results demonstrate feasibility. Next steps include expanding the size of the quantum hidden layer and increasing the variety of output image options.

quant-ph↗

arXiv2021

Paradigm selection for Data Fusion of SAR and Multispectral Sentinel data applied to Land-Cover Classification

Data fusion is a well-known technique, becoming more and more popular in the Artificial Intelligence for Earth Observation (AI4EO) domain mainly due to its ability of reinforcing AI4EO applications by combining multiple data sources and thus bringing better results. On the other hand, like other methods for satellite data analysis, data fusion itself is also benefiting and evolving thanks to the integration of Artificial Intelligence (AI). In this letter, four data fusion paradigms, based on Convolutional Neural Networks (CNNs), are analyzed and implemented. The goals are to provide a systematic procedure for choosing the best data fusion framework, resulting in the best classification results, once the basic structure for the CNN has been defined, and to help interested researchers in their work when data fusion applied to remote sensing is involved. The procedure has been validated for land-cover classification but it can be transferred to other cases.

cs.LG↗

arXiv2020

A New Mask R-CNN Based Method for Improved Landslide Detection

This paper presents a novel method of landslide detection by exploiting the Mask R-CNN capability of identifying an object layout by using a pixel-based segmentation, along with transfer learning used to train the proposed model. A data set of 160 elements is created containing landslide and non-landslide images. The proposed method consists of three steps: (i) augmenting training image samples to increase the volume of the training data, (ii) fine tuning with limited image samples, and (iii) performance evaluation of the algorithm in terms of precision, recall and F1 measure, on the considered landslide images, by adopting ResNet-50 and 101 as backbone models. The experimental results are quite encouraging as the proposed method achieves Precision equals to 1.00, Recall 0.93 and F1 measure 0.97, when ResNet-101 is used as backbone model, and with a low number of landslide photographs used as training samples. The proposed algorithm can be potentially useful for land use planners and policy makers of hilly areas where intermittent slope deformations necessitate landslide detection as prerequisite before planning.

cs.CV↗

arXiv2020

Automatic Dataset Builder for Machine Learning Applications to Satellite Imagery

Nowadays the use of Machine Learning (ML) algorithms is spreading in the field of Remote Sensing, with applications ranging from detection and classification of land use and monitoring to the prediction of many natural or anthropic phenomena of interest. One main limit of their employment is related to the need for a huge amount of data for training the neural network, chosen for the specific application, and the resulting computational weight and time required to collect the necessary data. In this letter the architecture of an innovative tool, enabling researchers to create in an automatic way suitable datasets for AI (Artificial Intelligence) applications in the EO (Earth Observation) context, is presented. Two versions of the architecture have been implemented and made available on Git-Hub, with a specific Graphical User Interface (GUI) for non-expert users.

eess.IV↗

arXiv2020

Application of DInSAR Technique to High Coherence Satellite Images for Strategic Infrastructure Monitoring

In this paper the authors present and validate a procedure, which intends to combine the latest state of the art models in bridge monitoring with freely available satellite data. Through the Differential SAR interferometry (DinSAR) technique, a dataset of displacements for the Morandi bridge in Genoa (Italy), before its collapse, has been created, by using images downloaded by the Copernicus Open-Access Hub and the ASFVertex Hub. The data have been processed through the ESA SNAP software to identify the rate of displacements in the parts of the bridge where collapse occurred. Results demonstrate that the adopted procedure has great potentiality in the application field, as it represents a simple and inexpensive method to monitor large structures in a continuous way, by helping to better quantify risks and guide effective mitigation countermeasures. Moreover, the same procedure, once properly validated, could be effectively extended to the current and future performance estimation of civil infrastructures.

eess.IV↗

arXiv2019

Landslide Geohazard Assessment With Convolutional Neural Networks Using Sentinel-2 Imagery Data

In this paper, the authors aim to combine the latest state of the art models in image recognition with the best publicly available satellite images to create a system for landslide risk mitigation. We focus first on landslide detection and further propose a similar system to be used for prediction. Such models are valuable as they could easily be scaled up to provide data for hazard evaluation, as satellite imagery becomes increasingly available. The goal is to use satellite images and correlated data to enrich the public repository of data and guide disaster relief efforts for locating precise areas where landslides have occurred. Different image augmentation methods are used to increase diversity in the chosen dataset and create more robust classification. The resulting outputs are then fed into variants of 3-D convolutional neural networks. A review of the current literature indicates there is no research using CNNs (Convolutional Neural Networks) and freely available satellite imagery for classifying landslide risk. The model has shown to be ultimately able to achieve a significantly better than baseline accuracy.

eess.IV↗