This paper discusses the concept and results of the BigDataOcean project, and specifically the anomaly detection pilot. While in the past, surveillance had suffered from a lack of data, current tracking technologies have transformed the problem into one of an overabundance of information, with needs which go well beyond the capabilities of traditional processing and algorithmic approaches. The major challenge faced today is developing the capacity to identify patterns emerging within huge amounts of data, fused from various sources and detecting outliers in a timely fashion, to act proactively and minimise the impact of possible threats. Within this context we first define an “anomaly”, before proceeding to present the BigDataOcean anomaly detection service; a service for the classification and early detection of anomalous vessel patterns. The service makes use of state-of-the-art big data technologies and novel algorithms which form the basis for a service capable of real time anomaly detection.