Multispectral Visual Incremental Knowledge Assimilation System (MUVIKAS)
Navy SBIR FY2015.1


Sol No.: Navy SBIR FY2015.1
Topic No.: N151-049
Topic Title: Multispectral Visual Incremental Knowledge Assimilation System (MUVIKAS)
Proposal No.: N151-049-0649
Firm: UtopiaCompression, Corporation
11150 W. Olympic Blvd.
Suite 820
Los Angeles, California 90064
Contact: Hieu Nguyen
Phone: (310) 473-1500
Abstract: Automated Target Recognition (ATR) technologies offer potential for automated detection and recognition of targets of interest in imagery data with enhanced accuracy. Most existing ATR algorithms are trained on fixed datasets and cannot change during deployment. As a consequence, these ATR systems are likely to have degraded performance when deployed at unseen environments that are not covered by the training data. Whenever new data or new classes of targets need to be added, the baseline approach is to retrain the ATR system from scratch. Such offline retraining usually demands significant amount of computations which causes operational downtime, and is not suitable for online during-mission analysis. Current systems also lack an efficient framework to interact with operator for online learning and adapting to new environments. In this project, UtopiaCompression Corp. (UC) proposes to build a novel MUlti-spectral Visual Incremental Knowledge Assimilation System (MUVIKAS) as a software program that facilitates in-situ target detection and classification in multi-spectral imagery with human in the loop. The system self-adapts to varying scene backgrounds and to inputs from human operator, based on a novel incremental ATR algorithm that perpetually assimilates new and relevant information into the existing knowledge database in an incremental fashion.
Benefits: Within the Navy, UC's proposed MUVIKAS system will be of immediate value to the COBRA Block I and II systems. UC's proposed product offering will offer a substantial ROI, as the MUVIKAS algorithms and optimization tools developed in this effort will reduce Navy program future operational costs by minimizing the time required for optimizing ATR algorithms to perform well in unseen operational environments. Apart from military applications, ATR technologies are widely used in intelligent systems in many civilian application domains including health care, surveillance and security, transportation etc. The proposed online learning technology is also of particular interest to applications involving information search with human in the loop.

Return