Skip to main content

Maritime Integrated Surveillance Awareness

Periodic Reporting for period 2 - MARISA (Maritime Integrated Surveillance Awareness)

Periodo di rendicontazione: 2018-11-01 al 2020-02-29

The MARISA project originates from the consideration that nowadays several threats prevail in the maritime domain that need to be handled through an improved situation awareness.
Large amount of unexploited maritime data requires intelligent correlation to produce higher level information. Benefits of information sharing needs to be taken at a next level to further improve coordination and cross-sectoral cooperation and interoperability at national and EU level.

MARISA focused on the following main challenges:

1. Deliver a toolkit providing a suite of services:
• to correlate and fuse heterogeneous and homogeneous data from different sources
• to improve information exchange, situational awareness, decision-making and reaction capabilities
2. Support the cooperation among different Member States and User Communities:
• providing networking and infrastructural services
• adopting the CISE data model as the basis for the definition of the MARISA data model
3. Comply with ethical and societal requirements set by EU fundamental rights and the General Data Protection Regulation:
• defining & implementing ethical requirements as project features
• defining the data protection policy for the project
The main ACHIEVEMENTS in the reporting period (M19-M34) can be summarized as follow:

1. Project coordination, risks and quality management (WP1)
2. Communication and dissemination activities, second and third MARISA Workshops (WP8)
3. Continuous animation of the MARISA User Community (WP2)
4. Revision and update of the user needs and operational trial scenarios (WP2, WP7)
5. Final Design of the MARISA Toolkit (WP3)
6. Finalization of the MARISA data fusion services (WP4)
7. Finalization of the MARISA common services (WP5)
8. Update of the integration and validation plan and procedures (WP6)
9. Update of detailed Operational Scenarios for Phase 2 Trials (WP7)
10. Planning and preparation of the operational trials for the second phase (WP7)
11. Finalization of the Training Kit (WP8)
12. Execution of the Second Phase Operational Trials (WP7)
13. Assessments of MARISA Phase-2 achievements (WP2)
14. Gathering of MARISA Final Workshop’s results (WP8)
15. Establishment of Exploitation Uptake actions (WP8)
16. Societal Ethical Final Reports delivering (WP1)

The five OPERATIONAL TRIALS have been successfully executed and the feedbacks have been collected by the practitioners through the conduction of four surveys (refers to [D7.7] for the detailed results):

1) User Requirements Survey
2) Situation Awareness Survey
3) System Usability Survey
4) Task Load Survey

The overall results have shown that there was a clear improvement from Phase 1 to Phase 2. In particular, a large percentage of user requirements were met in Phase 2 (about 96% overall).
The progress Beyond State of The Art of each significant innovation is reported in the following (reference service name is reported in squared parenthesis):

1) First adaptor enabling ingestion of CISE data in a Big Data Warehouse [CISE Adaptor]
2) Use of open Inter VTS Exchange Format for the service that is able to receive an IVEF data stream and adapt the vessel data to the internal MARISA data model [IVEF Receiver]
3) Use of a parallel and distributed approach based on big data design principles to efficiently compute traffic density maps from huge volumes of data collected by worldwide terrestrial and satellite networks of AIS receivers [AIS Density Map]
4) New algorithms to detect ships in order to decrease false alarms in difficult sea conditions (low wind areas with small local pixel value variations and high wind areas with peaks created by the breaking waves pattern, both sources of false alarms for traditional CFAR detectors) and to better estimate ships parameters (e.g. heading, length, width). Spatial Resolution: from 5 to 30 m (depending on input SAR satellite data); Temporal Resolution: from 1 to 8 data/day at our latitudes, in two time windows (dawn/dusk orbits) [Satellite Vessel Detection - SAR]
5) Integration of OSINT from the Open Source Global Database of Events (GDELT) identifying and classifying maritime safety and security events from multiple languages to improve the Maritime Situation Awareness [Events Detection from Global Database of Events – GDELT]
6) Use of VHR optical data and SAR data, also open sources when available, with more accurate vessels parameters estimation [Satellite Vessel Density Map]
7) Integration of both satellite derived and ground based AIS data, incremental population of the map along with the service activation period, for a specified AOI. Full integration within the MARISA multi-service Toolkit [Satellite AIS Density Map]
8) Improvement of the situational awareness providing all available different vessels' data including characteristics, images, videos, anomalies, alarms and threats [Vessel Data Association]
9) Track fusion algorithms designed to avoid data duplication on maritime picture through a data management strategy based on the innovative concept of M-track data entity. The M-track handles the full-time perspective of a vessel when it is monitored by several independent legacy systems along its track history [Multi-Common Operative Picture - M-COP]
10) Multiple techniques applied to ensure state-of-art analysis regarding maritime professional procedures, manures and route calculations. These base of knowledge is then applied in multiple beyond stare-of-art techniques in multivariate time-series anomaly detection to deliver robust and efficient algorithms for multiple abnormal situations described in user requirements [On-Line and Off-line Anomaly Detection Service - ADS/SRMS]
11) Geospatial Complex Event Processing based on the Event Processing Language (EPL). Configurable rules based on the events to be detected. Supports the combination of simple rules to achieve complex rules for higher level abnormal behaviour. Ability of including external sources of contextual information (e.g. sea/meteo conditions, historic patterns) in Dynamic Bayesian Networks which improves the detection of abnormal behaviours [Geospatial Complex Event Processing]
12) Ability to filter on a large amount of data (Big Data Storage components) . Distributed and scalable service [Business Intelligence Reports]
13) Use of VHR optical data and SAR data, also Open Source when available, with more accurate vessels’ parameters estimation, while providing this capability within the MARISA toolkit [Satellite Vessel Detection Anomalies; Satellite Vessel Prediction]
14) Planning of Missions based upon predicted and historical vessels' routes optimized using detected Alarms, Risks and Meteo conditions [Mission Planning]
15) Situational picture, advanced multilevel visualization allowing situation analysis from different points of view. Use of the most advanced techniques of data visualization, especially for what concerns the ease of discrimination of the target of interest vs. the rest of the picture; on the other side, the design of MARISA user’s interfaces is based on the most modern principles of usability, so as to avoid the user to be overwhelmed by a huge and unmanageable amount of information [MARISA HCI console]