Visual Analytics for the Detection of Anomalous Maritime Behavior

Abstract

The surveillance of large sea areas often generates huge amounts of multidimensional data. Exploring, analyzing and finding anomalous behavior within this data is a complex task. Confident decisions upon the abnormality of a particular vessel behavior require a certain level of situation awareness that may be difficult to achieve when the operator is overloaded by the available information. Based on a visual analytics process model, we present a novel system that supports the acquisition of situation awareness and the involvement of the user in the anomaly detection process using two layers of interactive visualizations. The system uses an interactive data mining module that supports the insertion of the user's knowledge and experience in the creation, validation and continuous update of the normal model of the environment.

A novel marine radar targets extraction approach based on sequential images and Bayesian Network

“…The ARPA function of marine radar is initially designed for collision avoidance, which does not concern the authenticity, importance or behaviour of blips (Yoo and Kim, 2003). Presently, in a busy waterway, pattern recognition of vessel behaviours becomes increasingly important, especially for port management (Riveiro et al, 2008). In this section, typical identification methods in radar image research are briefly reviewed.…”

Information visualisation for efficient knowledge discovery and informed decision in design by shopping

“…In the field of monitoring and supervision, Ireson (2009) states that "the management of this mass of information is crucial in aiding the decision-making process, ensuring, as far as possible, that the responders have full situational awareness to make informed decisions". With the same idea, Bass (2000) and Riveiro, Falkman, and Ziemke (2008) indicate the need for "situational awareness" for the formulation of an informed decision. Bass adds the need for "fusing data into information and knowledge, so network operators can make informed decisions" (Bass 2000).…”

“…These are: "knowledge and insight gain", "visualization", "analysis and treatment" and "manipulation and management". 2000Knowledge and insight gain Sullivan et al (2001), Keim et al (2006Keim et al ( , 2008aKeim et al ( , 2008b, Glaser and Tolman (2008) Lurie and Mason (2007), Wood, Otto, and Antonsson (1992), Petersen and Svendsen (2010), Mavris, Pinon, and Fullmer Jr (2010), Riveiro, Falkman, and Ziemke (2008), Meyer et al (2010) Analysis and treatment Keim et al (2006Keim et al ( , 2008aKeim et al ( , 2008b, Russell, Chiu, and Korde (2009), Meyer et al (2010), Riveiro, Falkman, and Ziemke (2008), Mavris, Pinon, and Fullmer Jr (2010)…”

Visualization of Vessel Traffic

“…Dykes et al [45] analyze these kind of trajectories with a combination of spatial views, such as maps and video, and standard multivariate views, such as parallel coordinate plots. Multiple views are used to understand reasons [122], which uses similar views, but also includes machine learning techniques, such as self-organizing maps shown in one of the views. Guo et al [65] propose a multiple view approach to investigate traffic crossing a road intersection and where direction of traffic plays a major role.…”