Category Archives: GeoInformatica

Exploring Cultural Heritage Sites with Digital Twins and Virtual Reality starting from real 3D data

Posted on by

Docente

Livio Pinto (mail)

Referente del progetto

Francesco Ioli – Federica Gaspari ( mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Digital Twin, VR, photogrammetry

Tecnologie da utilizzare

Languages: Javascript, Unity
Suggested: Python, basic of C/C# (for Unity scripting)

Descrizione (max 500 caratteri)

The goal of the project is to develop an immersive and user-friendly platform for exploring cultural heritage sites using Digital Twins and Virtual Reality (VR). The platform will use real 3D data (i.e., point cloud and meshes) collected from cultural heritage sites with various techniques such as UAV photogrammetry and laser scanning and integrate it with other relevant data such as images, labels, text, or sensor data to create a digital twin of the site. The platform will be intuitive, allowing non-expert users to easily explore and interact with the site.

Semi-automatic classification and cost calculator for women street names (“Las Calles de las Mujeres”) using OpenStreetMap, InstructGPT API, and Wikipedia API

Posted on by

Docente

Maria Brovelli (web, mail)

Referente del progetto

Angelly Pugliese (web, mail)

Area di ricerca

Web, multimedia e database

Keyword (max 3 separate da virgola)

Machine Learning, Gender Gap

Tecnologie da utilizzare

– Programming language: Javascript.
– Tools/APIs: OpenStreetMap API, InstructGPT, Wikipedia API.
– The development of this project is to be integrated with this project.

Descrizione (max 500 caratteri)

This project encompasses the creation of a working script/project that can generate a dataset of a city to be included in the platform “Las Calles de las Mujeres”.
This should be done using OSM, the InstructGPT API (OpenAI), and the Wikipedia API.
As the InstructGPT API has a cost, the core of the project is to use the free credits that OpenAI provides to create a functional script, and then create a calculator that tells the approximate cost of mapping a given city with the script.

5. Analysis of global distribution of Level 2A Sentinel-2 products

Posted on by

Docente

Giovanna Venuti (mail)

Referente del progetto

dott.ssa Daniela Stroppiana ( mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Earth Observations, Multispectral imagery, Sentinel 2

Tecnologie da utilizzare

Google Earth Engine

Descrizione (max 500 caratteri)

This project will be carried out in GEE with the objective of analysing the availability of Level 2A Sentinel-2 images at global scale in the GEE catalogue. The project will be carried out by developing GEE code for accessing the archive and metadata to depict the spatio-temporal distribution of image data and eventually their characteristics (from metadata).

Comparison of spatio-temporal burned area distribution

Posted on by

Docente

Giovanna Venuti (mail)

Referente del progetto

Dott.ssa Daniela Stroppiana ( mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Burned areas, Earth Observations, Time series

Tecnologie da utilizzare

Python, R

Descrizione (max 500 caratteri)

This project aims at comparing the spatio-temporal distribution of burned area estimates derived from multi-annual BA products available at global scale and derived from satellite data. The comparison will be carried out by year, country, biome, and taking into account other factors that could influence fires. Ad hoc code must be developed for the comparison of raster grid products.

Analysis of factors affecting wildfire distribution

Posted on by

Docente

Giovanna Venuti (mail)

Referente del progetto

Dott.ssa Daniela Stroppiana ( mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Burned areas, Earth Observation, Google Earth Engine

Tecnologie da utilizzare

Google Earth Engine

Descrizione (max 500 caratteri)

This project has the objective of using the Google Earth (GEE) catalogue (burned areas, land cover, and other ancillary datasets) for analysing the relative importance of factors affecting burned areas globally. The approach will be based on machine learning algorithms (e.g. Random forest) to be implemented in GEE.

Analysis of satellite SAR data over burned areas in African ecosystems

Posted on by

Docente

Giovanna Venuti (mail)

Referente del progetto

Dott.ssa Daniela Stroppiana ( mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Burned Areas, SAR, Earth Observation

Tecnologie da utilizzare

Google Earth Engine

Descrizione (max 500 caratteri)

This project aims at analysing the burned area signal with SAR Sentinel-1 data over areas affected by fires in African biomes (forest and savanna). The project foresees the integration of information on fire perimeters derived from Sentinel-2 multi-spectral images and backscatter signal in SAR Sentinel-1 data. The analysis will be carried out in Google Earth Engine.

Multi-fidelity, adaptive technique in design-exploration space, ANOVA-analysis

Posted on by

Docente

Ludovico Biagi (mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

Prediction, samplets

Tecnologie da utilizzare

python, C++, binding, I/O on dataset

Descrizione (max 500 caratteri)

Goal This project aims to develop additional features, e.g. multi-fidelity, adaptive technique in design-exploration space, ANOVA-analysis. The results will be tested on industrial testcase of WindAssistant Trasoceanic Cargo, Energy System and on geoinformatics data (e.g. GNSS dataset).
Project Plan :
• Read and understand a reference paper on samplets, kernel-based methods, multifidelity (provided)
• Getting familiar with Bayesian Optimization, Anova, MultiFidelity algorithms
• Design, train and implement the studied algorithms
• Performance assessment on an industrial dataset as well as on geoinformatics dataset
• Cowriting a report for scientific dissemination in ECCOMAS conference and for peer-review paper

Beidou satellites orbit

Posted on by

Docente

Ludovico Biagi (mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

GNSS, Beidou, orbits

Tecnologie da utilizzare

Python

Descrizione (max 500 caratteri)

The student will implement libraries to compute and plot orbits of Beidou satellites from RINEX broadcast ephemerides

Statistical analysis of computational tests of algorithms and heuristics

Posted on by

Following Coffin and Saltzman (2000), a statistical analysis of computational tests of algorithms and heuristics is designed for evaluating the performance of computer implementations of the algorithms. Some case studies are simulated, and a statistically rigorous data analysis of the results obtained is carried out using Python; in particular, multivariate exploratory data analysis, multiple linear regression, and multiple comparisons (Anova and Tukey post-hoc Intervals; nonparametric global test and post-hoc tests) will be used.

Efficient Outliers rejection in positioning of mobile devices

Posted on by

Docente

Ludovico Biagi (mail)

Area di ricerca

Geoinformatica

Keyword (max 3 separate da virgola)

GNSS, Efficient Leave One Out

Tecnologie da utilizzare

Python

Descrizione (max 500 caratteri)

GNSS provide positions estimates that are quite accurate in a good observation environment. However, in harsh conditions, blundered observations can seriously affect the accuracy of the estimated positions.
The Leave One Out method is really accurate in identifying blunders but is not efficient from a numerical point of view: this is clearly a serious problem for real time applications.
An efficient LOO method has been studied. The student will implement it and apply it to simulated GNSS data to test accuracy and efficiency.