Objective Sensor Manipulation for Optimized Submarine Imaging Systems (OSMOSIS)
Navy SBIR FY2018.1

Sol No.: Navy SBIR FY2018.1
Topic No.: N181-066
Topic Title: Objective Sensor Manipulation for Optimized Submarine Imaging Systems (OSMOSIS)
Proposal No.: N181-066-0423
Firm: Charles River Analytics Inc.
625 Mount Auburn Street
Cambridge, Massachusetts 2138
Contact: Ross Eaton
Phone: (617) 491-3474
Web Site: http://www.cra.com
Abstract: The Submarine Force is phasing out conventional optical periscopes in favor of digital sensor masts that electronically transmit video to the Control Center. However, digital imagery suffers from distortions due to weather and lighting variations in the scene and water on the lens, which in turn, decreases watchstandersâ?T situational awareness and ability to detect targets. While methods for improving these image degradations exist, they must be applied manually by skilled operators. We propose to develop Objective Sensor Manipulation for Optimized Submarine Imaging Systems (OSMOSIS) to automatically assess image quality and recommend enhancements for the operator to apply. OSMOSIS consists of two main software components. First, an automated image quality monitoring component analyzes input imagery and computes a General Image Score (GIS), which is higher for better quality images and decreases as image quality degrades (e.g., as motion blur or noise level increases). When GIS drops too low, OSMOSIS warns the watchstander that poor image quality could compromise situational awareness. The second component, an image enhancement wizard, then suggests camera parameter changes, filters, and image processing algorithms to improve image quality. Once the corrections are applied, OSMOSIS continues to monitor image quality and provide feedback to watchstanders.
Benefits: The proposed technology will have an immediate application to Navy submarine imaging systems by providing an objective measure of image quality and suggestions for image quality improvement. Navy surface ships also make use of EO/IR sensors for improved situational awareness and could benefit from automatic image quality measurement. OSMOSIS will also serve as a key building block for an intelligent marine autopilot product in development at Charles River Analytics.