The main objective of this activity is to develop general analytical methods for the exploitation of the information contained in Satellite Image Time Series -SITS.

 

 

The access to the information content of Satellite Image Time Series (SITS) is of high relevance for enlarging the functionalities of EO Payload Ground Segment (PGS) systems and next-generation of services for enhanced and long-term data exploitation of already acquired and forthcoming data.

The main objective of this activity is to develop general analytical methods for the exploitation of the information contained in SITS. The main focus is therefore on information extraction in the form of "categories of evolution" and elaboration of technologies to classify the evolution processes of observed scenes. The concept is to model an image time series based on the transformations occurring between consecutive acquisitions in the considered SITS. Complementary information about the changes occurred in the scenes will be extracted and further employed in order to provide the user with a broader perspective on the transformation and evolution processes.

 

In such a context, key issues to be addressed are the technology analysis, development and benchmarking to enable:

 

• Quick and effective generation of SITS.

• Definition and categorisation of classes having the same evolution in time.

• Fast semantic searches of defined classes within huge image archives.

 

The project shall address as well the SITS specific algorithm selection and benchmarking, as well as the validation of prototypes with user communities.

The need to access and interpret EO data time series is strongly increasing during last years for a broad areas of applications. In particular, there is a growing interest on global change monitoring, which requires data time series spanning 20 years and more. Considering the spatial resolution of new sensors, giving access to detailed image structures, the opportunity to compose and analyse high-resolution SITS should be exploited. The observation of dynamic and precise spatio-temporal structures is getting more and more appealing.