Fabiana Di Ciaccio

Dr. Fabiana Di Ciaccio

University of Florence, Florence, Tuscany, Italy
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
22 February 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Paolo RussoPaolo Russo
Paolo Russo
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
Salvatore TroisiSalvatore Troisi
Salvatore Troisi
One of the main issues for the navigation of underwater robots consists in accurate vehicle positioning, which heavily depends on the orientation estimation phase. The systems employed to this end are affected by different noise typologies, mainly related to the sensors and to the irregular noise of the underwater environment. Filtering algorithms can reduce their effect if opportunely configured, but this process usually requires fine techniques and time. This paper presents DANAE++, an improved denoising autoencoder based on DANAE (deep Denoising AutoeNcoder for Attitude Estimation), which is able to recover Kalman Filter (KF) IMU/AHRS orientation estimations from any kind of noise, independently of its nature. This deep learning-based architecture already proved to be robust and reliable, but in its enhanced implementation significant improvements are obtained in terms of both results and performance. In fact, DANAE++ is able to denoise the three angles describing the attitude at the same time, and that is verified also using the estimations provided by an extended KF. Further tests could make this method suitable for real-time applications in navigation tasks.

10 March 2019 in Sensors
Verified
Journal Article
Open access
PDF file
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
PMPaolo Menegazzo
Paolo Menegazzo
Salvatore TroisiSalvatore Troisi
Salvatore Troisi
Aids to Navigation (AtoN) are auxiliary devices intended to support maritime navigation. They include both traditional signals (e.g., buoys and lights) and electronic aids, as for example those transmitted to ships through automatic tracking systems. In both cases, international organizations together with local authorities define technical specifications and standards on their use. Work still being finalized in the Venetian Lagoon made it necessary an assessment of the existing signaling system to guarantee the maximum level of safety in the waterways. Considering the severe atmospheric conditions to which the Lagoon is frequently subjected and the bathymetry restrictions affecting the navigation, an alternative aid system has been formalized for the first time in Italy. It is based on electronic and identification devices employed to virtualize the AtoN that will not be located at sea but only remotely identified by their coded messages, thus guaranteeing the continuity of port operations in any visibility conditions. This paper presents the procedures followed to reach a solution in line with the safety and efficiency standards given for the AtoN systems, considering position and luminous characteristics of physical signals in the first case, theoretical and statistical studies on Virtual AIS AtoN placement in the second case.

5 October 2023 in Ecological Questions
Verified
Journal Article
Open access
PDF file
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
The widespread interest towards a sustainable and effective monitoring of the environment is increasingly demanding the development of modern and more affordable technologies to support or even replace the traditional time-consuming, high-cost sampling surveys at a multi-scale level. Researchers are highly benefitting from the recent enormous progresses achieved in the Artificial Intelligence (AI) field, with Machine/Deep Learning (ML/DL) applications increasing at sight. This gives a remarkable contribution to the environmental monitoring at sea, further allowing to develop efficient, smart and low-cost solutions to support the wide variety of tasks dealing with this objective. This study explores the global scientific literature on AI and ML/DL applications for the environmental monitoring over the last years. The VOSviewer software has been used to create maps based on the bibliographic network data: this allowed to display the relationships among scientific journals, researchers, and countries and to analyze the co-occurrence of different terms connected to the research. The resulting bibliometric analysis aims at verifying the major research interests and at providing the community with interesting findings and new perspectives on this very important topic, highlighting the great potential and flexibility of these methodologies and the excellent achievements they obtained in the last years.

31 May 2023 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
FRFrancesca Russo
Francesca Russo
Silvio Del PizzoSilvio Del Pizzo
Silvio Del Pizzo
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
Salvatore TroisiSalvatore Troisi
Salvatore Troisi
The Posidonia oceanica meadows represent a fundamental biological indicator for the assessment of the marine ecosystem’s state of health. They also play an essential role in the conservation of coastal morphology. The composition, extent, and structure of the meadows are conditioned by the biological characteristics of the plant itself and by the environmental setting, considering the type and nature of the substrate, the geomorphology of the seabed, the hydrodynamics, the depth, the light availability, the sedimentation speed, etc. In this work, we present a methodology for the effective monitoring and mapping of the Posidonia oceanica meadows by means of underwater photogrammetry. To reduce the effect of environmental factors on the underwater images (e.g., the bluish or greenish effects), the workflow is enhanced through the application of two different algorithms. The 3D point cloud obtained using the restored images allowed for a better categorization of a wider area than the one made using the original image elaboration. Therefore, this work aims at presenting a photogrammetric approach for the rapid and reliable characterization of the seabed, with particular reference to the Posidonia coverage.

12 May 2020 in Applied Geomatics
Verified
Journal Article
Closed access
PDF file
LALuca Alessandri
Luca Alessandri
Valerio BaiocchiValerio Baiocchi
Valerio Baiocchi
Silvio Del PizzoSilvio Del Pizzo
Silvio Del Pizzo
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
MOMatteo Onori
Matteo Onori
Salvatore TroisiSalvatore Troisi
Salvatore Troisi

2 September 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
RARiccardo Angelini
Riccardo Angelini
EAEduard Angelats
Eduard Angelats
FRFrancesca Ribas
Francesca Ribas
GLGuido Luzi
Guido Luzi
Fabiana Di CiaccioFabiana Di Ciaccio
Fabiana Di Ciaccio
Andrea MasieroAndrea Masiero
Andrea Masiero
Shoreline extraction from Synthetic Aperture Radar (SAR) imagery has been increasingly explored due to its all-weather, day-and-night observation capabilities. In this study, a robust methodology for automatic shoreline detection was developed and validated using SAR data from Sentinel-1 (S1, 20 images) and TerraSAR-X (TSX, 2 images). SAR images acquired over four microtidal Mediterranean sandy and gravel beaches were processed using a multi-step workflow that included preprocessing, noise reduction, land-sea segmentation by clustering or thresholding methods, shoreline extraction, and outlier detection techniques. The accuracy of the SAR-derived shorelines was evaluated against reference ones obtained from high-resolution aerial orthomosaics or PlanetScope imagery. The results of the S1 analyses demonstrated excellent accuracy and stability for gravel beaches (approximately 6 m of mean absolute deviation, MAD), and for sandy beaches (approximately 7 m of MAD), in this latter case with significant variations observed between the two sites. In a comparative assessment, TSX data achieved higher accuracy in terms of MAD (2.5 m) compared to S1 (6.5 m) in the same context, but only in the image with good meteorological conditions (no differences were obtained in the other date). In general, the use of the Block-matching and 3D filtering (BM3D) filter significantly improved image quality, reducing noise artifacts and enhancing the contrast between land and sea, especially in not-perfect meteorological conditions, which usually influenced SAR-derived shoreline accuracy. Using 3 classes in the classification also produced better results, and outlier detection played a minor role. Overall, this study demonstrates that the innovative integration of advanced image processing techniques and classification algorithms significantly enhances the reliability of SAR-based shoreline detection. The findings underscore the potential of SAR imagery as a valuable tool for coastal monitoring. Achieving an accuracy close to that obtainable with multispectral data, shoreline extracted from SAR could be successfully used in areas with frequent cloud cover or limited optical data availability.