Plenary Event
Tuesday Track Plenary
On demand | Presented Live 5 April 2022
8:00 AM
Welcome and Acknowledgements
8:05 AM to 8:45 AM
Automatic target recognition: past, present, future
Edmund Zelnio, Autonomy Technology Research Center in AFRL (United States)
Automatic target recognition is an important technology that has numerous important applications. This technology is presented by examining the current state of the art and then reviewing the past from a statistical pattern recognition perspective to follow the evolution into the deep learning approaches popular today. However, automatic target recognition has additional challenges that are outside the sweet spot of current deep learning approaches. To look to the future, key technical challenges are outlined and a way forward is proposed to accelerate automatic target recognition technology development.
Edmund Zelnio graduated from Bradley University, Peoria, IL, in 1975 and has pursued doctoral studies at The Ohio State University in electromagnetics and at Wright State University in signal processing. During his 46-year career with the Air Force Research Laboratory (AFRL), Wright Patterson Air Force Base, Ohio, he has spent 44 years working in the area of automated exploitation of imaging sensors, primarily addressing synthetic aperture radar. He is a former division chief and technical advisor of the Automatic Target Recognition Division of the Sensors Directorate in AFRL and has served in an advisory capacity to the Department of Defense and the intelligence community. He has served as the chair of the SPIE Algorithms for Synthetic Aperture Radar Imagery conference for the past 26 years. He is currently the director of the Autonomy Technology Research Center in AFRL. He is the recipient of the 53rd Department of Defense Distinguished Civilian Service Award and is an AFRL Fellow.
8:45 AM to 9:30 AM
DoD's AI sensor processing
Jill Crisman, Principal Director for Artificial Intelligence, U.S. Department of Defense (United States)
Today’s AI, namely deep learning and neural networks, are fundamentally changing how software can be created. Deep neural networks are becoming more prevalent in processing the tsunami of data collected by sensors to extract important information. In this talk, we will overview Department of Defense’s sensors and processing Science and Technology portfolio and highlight a few examples of the exciting work.
Jill Crisman is the principal director for Artificial Intelligence (AI) in the Office of the Director of Defense Research and Engineering (Modernization) within the Office of the Under Secretary of Defense for Research and Engineering (OUSD(R&E)). She is responsible for developing the department-wide AI roadmap and unifying and coordinating the Department's plans and investments to achieve a competitive advantage in AI. She will be emphasizing the engineering required to transform AI research into operational AI in collaboration with the Joint Artificial Intelligence Center (JAIC) and the Services. Jill Crisman joined OUSD(R&E) after serving as the chief scientist at the JAIC where, as part of the leadership team, she helped to stand up the organization. Previously, she was the chief scientist at Next Century Corporation and a program manager at the U.S. Intelligence Advanced Research Projects Activity (IARPA). Her primary interest is in the field of machine perception, planning, and interfaces that significantly enhance human/machine collaboration. She holds a Doctorate of Philosophy in Electrical and Computer Engineering from Carnegie Mellon University, where her thesis created some of the first perception algorithms for self-driving cars. She was an Associate Professor and director of the Robotics and Computer Vision Systems at Northeastern University and a founding faculty member of the Franklin W. Olin College of Engineering.
Welcome and Acknowledgements
8:05 AM to 8:45 AM
Advanced Sensing and Imaging Track Plenary
Automatic target recognition: past, present, future
Edmund Zelnio, Autonomy Technology Research Center in AFRL (United States)
Automatic target recognition is an important technology that has numerous important applications. This technology is presented by examining the current state of the art and then reviewing the past from a statistical pattern recognition perspective to follow the evolution into the deep learning approaches popular today. However, automatic target recognition has additional challenges that are outside the sweet spot of current deep learning approaches. To look to the future, key technical challenges are outlined and a way forward is proposed to accelerate automatic target recognition technology development.
Edmund Zelnio graduated from Bradley University, Peoria, IL, in 1975 and has pursued doctoral studies at The Ohio State University in electromagnetics and at Wright State University in signal processing. During his 46-year career with the Air Force Research Laboratory (AFRL), Wright Patterson Air Force Base, Ohio, he has spent 44 years working in the area of automated exploitation of imaging sensors, primarily addressing synthetic aperture radar. He is a former division chief and technical advisor of the Automatic Target Recognition Division of the Sensors Directorate in AFRL and has served in an advisory capacity to the Department of Defense and the intelligence community. He has served as the chair of the SPIE Algorithms for Synthetic Aperture Radar Imagery conference for the past 26 years. He is currently the director of the Autonomy Technology Research Center in AFRL. He is the recipient of the 53rd Department of Defense Distinguished Civilian Service Award and is an AFRL Fellow.
8:45 AM to 9:30 AM
Next Generation Sensor Systems and Applications Track Plenary
DoD's AI sensor processing
Jill Crisman, Principal Director for Artificial Intelligence, U.S. Department of Defense (United States)
Today’s AI, namely deep learning and neural networks, are fundamentally changing how software can be created. Deep neural networks are becoming more prevalent in processing the tsunami of data collected by sensors to extract important information. In this talk, we will overview Department of Defense’s sensors and processing Science and Technology portfolio and highlight a few examples of the exciting work.
Jill Crisman is the principal director for Artificial Intelligence (AI) in the Office of the Director of Defense Research and Engineering (Modernization) within the Office of the Under Secretary of Defense for Research and Engineering (OUSD(R&E)). She is responsible for developing the department-wide AI roadmap and unifying and coordinating the Department's plans and investments to achieve a competitive advantage in AI. She will be emphasizing the engineering required to transform AI research into operational AI in collaboration with the Joint Artificial Intelligence Center (JAIC) and the Services. Jill Crisman joined OUSD(R&E) after serving as the chief scientist at the JAIC where, as part of the leadership team, she helped to stand up the organization. Previously, she was the chief scientist at Next Century Corporation and a program manager at the U.S. Intelligence Advanced Research Projects Activity (IARPA). Her primary interest is in the field of machine perception, planning, and interfaces that significantly enhance human/machine collaboration. She holds a Doctorate of Philosophy in Electrical and Computer Engineering from Carnegie Mellon University, where her thesis created some of the first perception algorithms for self-driving cars. She was an Associate Professor and director of the Robotics and Computer Vision Systems at Northeastern University and a founding faculty member of the Franklin W. Olin College of Engineering.