BrainMap

Mr. Teodor Costachioiu

- UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI

Researcher

Expertise & keywords

Platform for fusion and management of multi-source data collections exploitable by artificial intelligence models for the estimation and predictive analysis of risk situations Call name: P 5.6 - SP 5.6.3 - Solutii
PN-IV-P6-6.3-SOL-2024-2-0251 2024 - 2026

Role in this project:

Coordinating institution: UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI

Project partners: UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI (RO); Academia Tehnică Militară „FERDINAND I” (RO); UNIVERSITATEA TRANSILVANIA BRASOV (RO); ESRI ROMANIA SRL (RO)

Affiliation:

Project website: http://ai4risk.ro

Abstract:

AI4RISK aims to strengthen national security by using machine learning technologies to analyze and interpret complex data from diverse sources in order to identify and anticipate potential security risks. The project aims to achieve an innovative solution for automatic collection and processing of satellite and aerial data collections by implementing generative methods to improve the characteristics of aerial images; the creation and implementation of containerized explainable artificial intelligence models, the implementation of the platform for predictive analysis and risk estimation based on user questions, the integration and visualization of data in the platform, through the implementation of mapping services and the rendering of real-time image streams.

In addition to the requirements formulated by the beneficiary, the consortium proposes for implementation in the AI4RISK platform a system for preparing and improving operators' reactions to risk incidents, through the use of machine learning techniques. It will allow operators to adapt/enable specific methodologies for data processing and status assessment. Therefore, analyzing the results and taking into account the information density of the map of the region of interest, the system will propose recommendations for further actions - such as the integration of a wider range of news sources, including in several languages, the activation of an extensive network of cameras for monitoring, the addition of additional data relating to targets in the area – all aimed at optimizing the operator's intervention strategy.

Long-Term Exploitation of Satellite Image Time Series Call name:
2014 - 2015

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI ()

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI ()

Project website:

Abstract:

The research project LEO-SITS aims at enhancing the functionalities of the EO Payload Ground Segment systems and the next-generation services for an enhanced and long term data expatiation of the ITS already acquired and to be continued by the Sentinels, with focus on Sentinel 2.

The need to reach historical Earth Observation (EO) data series strongly increased in the last years, mainly for environmental monitoring applications. This trend is likely to increase even more in the future in particular for the growing interest on global change monitoring that requires data time-series spanning 20 years and more. Considering new sensors spatial resolution giving access to detailed image structures, the opportunities to compose high-resolution satellite image time-series (SITS) are growing and the observation of precise spatio-temporal structures in dynamic scenes is getting more and more accessible.

Dedicated tools for information extraction in SITS have been developed in order to perform change detection, monitoring, or validation of physical models. However, these techniques usually are dedicated to specific applications. Consequently, in order to exploit the information contained in SITS, general analytical methods are required.

This project is focused on information extraction in the form of categories of evolution. Project goal is to develop algorithms and techniques to classify the evolutions of several categories inside a scene. It is of great importance for a user searching in SITS archives to find and delimitate classes having the same evolution in time.

The main idea is to model an image time series based on the transformations occurring between consecutive acquisition of the considered SITS. The novelty of the proposed technique lays in the conversion of the multispectral information from the entire data set into a change map time series (CMTS).

Pairs of consecutive images will be described by a number of change maps computed using similarity measures. Complementary information about the changes occurred in the scene will be extracted and further employed in order to provide the user with a broader perspective on the land transformation processes.

EXTRACTION OF SPATIO-TEMPORARY INFORMATION FROM SEQUENCE OF MULTIDIMENSIONAL SIGNALS FOR DETECTION OF CHANGES Call name:
PN II, CNCSIS: cod 1247 2009 - 2011

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI ()

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI ()

Project website: https://uefiscdi.gov.ro/userfiles/file/COMISIA%202/2010/02_DECEMBRIE_Calculatoare/LAZARESCU%20VASILE_ID1247_2008.pdf

Abstract:

The present project aims to approach new methods of data investigation and processing in order to obtain knowledge directly exploitable by a human user, from very large volumes of data that do not have an obvious coherence. Data mining (DM) means the search operations of patterns that are of interest for a particular form of representation or for a set of such representations. For the spatio-temporal sequences, which store the evolution in time of the objects, the data mining techniques follow the identification of the patterns that appear frequently, in order to detect the changes. for example, for satellite images of a geographical region mining aims to determine patterns that describe the location or movement in time of objects or those that describe the evolution of natural phenomena, such as vegetation status, evolution of meteorological phenomena, evolution of resources.

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects