Automated Image Understanding for Maritime Threat Analysis (AIUMTA)

Project Description

The Maritime Activity Analysis Workbench (MAAW) is a ground-breaking intelligent system that learns to detect suspicious maritime activity near ports and harbors by analyzing surveillance video, improving the US Navy's capability to secure ports and harbors.

We collaborated with the Navy Center for Applied Research in Artificial Intelligence (NCARAI) at the Naval Research Laboratory (NRL) to develop MAAW and new machine learning approaches for maritime image processing and situation understanding.

Accomplishments

We demonstrated that object and activity recognition can be improved by incorporating contextual information into relational learning algorithms. We explored the the performance characteristics and differences between local and global anomaly detection algorithms on difficult borderline anomalies and demonstrated that global algorithms outperform the local algorithms on tracks that are unstructured and highly variable.