Quarterly Report for 2/25/2006-05/24/2006
Abstract
This research effort is focusing on development of adaptive sensing algorithms for asymmetric threats. The algorithms are particularly targeted towards use with data from multi-camera video surveillance systems. We are not attempting to model the infinite class of asymmetric targets, since these are generally unpredictable and therefore limited if any a priori sensor data are available for these threats. Rather, we model normal or typical behavior using statistical algorithms. Key challenges that are being addressed in the current effort: * Statistical characterization of background events * Tracking of foreground objects * Statistical characterization of object dynamics (via HMMs), in the presence of occlusions and uncertainty of object pose and motion *Multi-aspect, multi-camera target recognition.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 25, 2006
- Accession Number
- ADA449189
Entities
Organizations
- Signal Innovations Group, Inc.