Your are currently viewing: Home Research Marine localization, pose estimation and classification

Posture Recognition for Automated Evaluation of MOUT Training

Detecting and classifying marines and their postures is critical for automated training performance evaluation.  The main objective for this project is to detect articulated objects in various configurations in still images, with an unconstrained, cluttered background that can not be modeled.  Our approach usesa  multi-class boosting procedure that favors discriminative features shared by multiple objects and views. Unlike traditional methods, this approach scales logarithmically with the number of classes. Click here to see a video.

The Behavioral Analysis and Synthesis for Intelligent Training (BASE-IT) is a project led by the NPS MOVES Institute, and is conducted in collaboration with research teams from Sarnoff Corporation and University of North Carolina (UNC) at Chapel Hill. This three-year-long project is sponsored by the Office of Naval Research (ONR) and represents a $6.5 million Navy investment in advancing technologies that will support USMC training for full spectrum operations in urban terrain. A primary objective of the BASE-IT project is to develop a state-of-the- art intelligent instrumentation system for physical training ranges.

For more, see the BASE-IT web pages.