Design and Validation of a Sensor Integration and Feature Fusion Test-Bed for Image-Based Pattern Recognition Applications
Hrishikesh V. Karvir · CORE Scholar (Wright State University) · 2010
Design and Validation of a Sensor Integration and Feature Fusion Test-Bed for Image-Based Pattern Recognition Applications.The collection, integration and interpretation of information to provide unified smart solutions have received tremendous attention in the last decade.With increasingly sophisticated algorithms and improvements in hardware technology, there exists a need for a cost-effective and standardized multi-source information fusion system.To deliver such a system, we integrated a sensor hardware test-bed using scientific grade commercial off-the-shelf (COTS) technology and developed supporting software tools that enable rapid prototyping.The validity of this test-bed and associated software was demonstrated through the delivery of a ground-based multispectral visual surveillance prototype for improvised explosive devices (IED) detection using electrooptical (EO) and short-wave infrared (SWIR) cameras.The prototype provided a portable and scalable solution for real-time synchronous acquisition from multiple imagers and its modular design conveniently accommodates new imaging sensors and requirements for different applications.Software developed to support the test-bed included modules for image acquisition, preconditioning, segmentation, feature extraction, data regularization and pattern recognition.Dynamic control of acquisition parameters through feedback from these modules facilitated optimized data collection.Whereas most current research related to automatic target detection her support and guidance throughout my master's and doctoral research.Her relentless pursuit for perfection motivated me to achieve excellence in every endeavor and develop to be a better researcher.I am equally thankful to all my committee members for being an integral part of my doctoral research experience.Dr. Hangartner timely advised and guided me throughout my research period.Dr. Narayanan provided me with financial and moral support when I needed it most.Dr. Oxley was always available for guidance, and more than once helped me resolve issues pertaining to pattern classification.Dr. Hong accepted my request for participating as a committee member at a crucial phase and provided important critical feedback.But most importantly, I would like to commemorate and