The 2017 edition of the IEEE International Conference on Big Data took place in Boston, MA, from 11 to 14 December [1]. The conference is one of the most prestigious events in the field of Big Data. The Centre for Research and Technological Innovation contributed to the conference by presenting a paper entitled “Real Time Semantic Enrichment of Broadcast Content in the Big Data Age” [2]. The paper describes the work that has been carried out in collaboration with Agile Lab and CELI Language Technology, and focused on the design and implementation of a proof-of-concept solution for searching, organising and accessing multimedia data in a fast and semantic-driven way.

The system supports real time ingestion of video streams on which different machine learning techniques (such as global and local visual features extraction and matching) are applied in a parallel and scalable way. The video processing pipeline is shown in the following figure.

First, a set of visual descriptors are extracted from the frames of the incoming stream. Extracted descriptors are matched to a reference database of visual patterns (e.g. buildings, paintings, monuments) in order to produce a set of meta-tags describing the ingested contents. Furthermore, these tags are semantically enriched using open semantic data repositories. The system is designed with a scale-out pattern architecture based on Apache Spark, ensuring high-performance in Big Data management environments. Further details can be found in [2].

[1] IEEE BigData 2017 Boston,MA,USA

[2] Maurizio Montagnuolo, Alberto Messina, Nicolò Bidotti, Paolo Platter, Alessio Bosca, “Real Time Semantic Enrichment of Broadcast Content in the Big Data Age”, 2017 IEEE International Conference on Big Data