Daniela Faur

Daniela Faur

Auto-generated profile, based on publicly available information

Daniela Faur

Center for Spatial Information, University Politehnica of Bucharest, Bucharest, Romania

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 January 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
VVVlad Vasilescu
Vlad Vasilescu
MDMihai Datcu
Mihai Datcu
DFDaniela Faur
Daniela Faur
Deep Learning methods have become ubiquitous tools in many Earth observation applications, delivering state-of-the-art results while proving to generalise for a variety of scenarios. One such domain concerns the Sentinel-2 satellite mission, which provides multi-spectral images in the form of 13 spectral bands, captured at 3 different spatial resolutions: 10m, 20m and 60m. This research aims to provide a super-resolution mechanism based on fully convolutional neural networks (CNNs) for up-sampling the low-resolution spectral bands of Sentinel-2 up to 10m spatial resolution. Our approach is centered on attaining good performance with respect to two main properties: consistency and synthesis. While the synthesis evaluation, also known as Wald’s protocol, has spoken for the performance of almost all previously introduced methods, the consistency property has been overlooked as a viable evaluation procedure. Recently introduced techniques make use of sensor’s modulation transfer function (MTF) to learn an approximate inverse mapping from low-resolution to high-resolution images, which is on a direct path for achieving a good consistency value. To this end, we propose a multi-objective loss for training our architectures, including a MTF-based mechanism, a direct input-output mapping using synthetically degraded data, along with direct similarity measures between high-frequency details from already available 10m bands and super-resolved images. Experiments indicate that our method is able to achieve a good trade-off between consistency and synthesis properties, along with competitive visual quality results.

17 May 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
INIulia Coca Neagoe
Iulia Coca Neagoe
DFDaniela Faur
Daniela Faur
CVCorina Vaduva
Corina Vaduva
MDMihai Datcu
Mihai Datcu
Multispectral (MS) remote sensing (RS) images are of great interest for various applications, yet, quite often, a MS product exhibits one or more noisy bands, strip lines or even missing bands which leads to decreased confidence in the information it contains. Meeting this challenge, the current paper proposes a UNet based neural network architecture to reconstruct a spectral band. The worst-case scenario is considered, that of a missing band, the reconstruction being performed based on the available bands. Besides the comparison with state of the art methods, both a qualitative and quantitative analysis is full-filled considering several metrics: Root-mean-square error (RMSE), Structural similarity index (SSIM), Signal to reconstruction error (SRE), Peak signal to noise ratio (PSNR) and Spectral angle mapper (SAM). The experiments focused on Sentinel-2 (S2) open data within the Copernicus programme. Various patterns of urban areas, agricultural regions, regions from North Pole or Kyiv, Ukraine are included in our dataset to prove the efficiency of band reconstruction regardless landcover diversity.

25 April 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
ICIulia Calota
Iulia Calota
DFDaniela Faur
Daniela Faur
MDMihai Datcu
Mihai Datcu
As Deep Learning attracts Earth Observation (EO) community's interest, the challenge to derive explainable, actionable information creates a bottleneck in EO models' development. Computer Vision proved that effective results of the DL algorithms imply a considerable amount of training data sets. This is not the case in EO where images are characterized by a broad variety of sensor data, ranging from multispectral to Synthetic Aperture Radar (SAR) with variable number of spectral bands, polarization or spatial resolution. In this paper we present effective methodologies for fast training with reduced data sets of simple deep neural networks, while preserving the similar performance of state of the art methods. The hybrid solutions we provide imply the reduction of input data dimension in a convolutional neural network. We replaced dataset's patches with histograms of pixel intensity, Bag-of-Words or down-sampled images. Following the proposed approaches, the training time and the dataset size are significantly reduced, while the performance of classification is preserved. These optimized implementations enable the deployment of lightweight deep learning models for real time processing tasks able to exhibit accurate results for instantce, a disaster management scenerio. We demonstrated the computational efficiency of these approaches on various, complex data, both multispectral and SAR, with different resolutions.

1 January 2008
Verified
Book Chapter
Closed access
PDF file
CVCorina Vaduva
Corina Vaduva
DFDaniela Faur
Daniela Faur
APAnca Popescu
Anca Popescu
IGInge Gavat
Inge Gavat
MDMihai Datcu
Mihai Datcu

21 September 2020
Verified
Conference Paper
Closed access
ICIulia Calota
Iulia Calota
DFDaniela Faur
Daniela Faur
MDMihai Datcu
Mihai Datcu
Deep Learning offers numerous techniques for data analysis and feature extraction, useful in Earth Observation. However, a persistent problem is the small number of labeled datasets and the variety of the data, due to the different instruments used for collecting scenes. For example, to what extent can a deep neural network handle image patches of different resolutions, and to what extent do we need very high-resolution images? In this paper, we study the impact of the resolution in SAR images on the capability of a convolutional neural network to classify urban scenes. The goal is to find urban classes that are recognizable in images with different resolution. We start by training a convolutional neural network on OpenSARUrban [14], a dataset with patches originating from high-resolution scenes (20 meters), and then we lower the resolution of the patches by several factors and train the same network on them. Finally, we need to apply these findings on “real” data. With this purpose, we present VHRUrbanSAR, a novel dataset containing 8234 SAR image patches of from very high-resolution scenes (5 meters), whose purpose in this work is fine-tuning. Both datasets have similar classes, which means that we can identify those urban classes that are recognized by both image types. We conclude that: (1) Reducing the resolution of the images by half has little effect on the performance; (2) Some classes in urban areas can be classified with a network trained on lower resolution images.

1 July 2019
Verified
Conference Paper
Open access
DFDaniela Faur
Daniela Faur
AGAndreea Griparis
Andreea Griparis
ASAdrian Stoica
Adrian Stoica
PMPhilippe Mougnaud
Philippe Mougnaud
MDMihai Datcu
Mihai Datcu
This paper introduces a tool designed to provide an innovative and insightful way of exploring Earth observation data content beyond visualization, by addressing a visual analytics process. The considered framework combines machine learning and visualization techniques, empowered through human interaction, to gain knowledge from the data. The proposed tool- eVADE leverages the methodologies developed in the fields of information retrieval, data mining and knowledge representation by the means of a visual analytics component. eVADE increases users capability to understand and extract meaningful semantic clusters together with quantitative measurements, presented in a suggestive visual way.